Skip to main content

Changelog

What's New

New models, features, and improvements shipped to PixelDojo.

Friendlier Nano Banana Reference-Image Limit Message

  • ๐ŸŒ
    Fixed

    Sending more than 14 reference images to Nano Banana used to surface the raw provider error "Runware: Invalid number of elements for 'referenceImages' parameter" โ€” confusing brand and parameter names with no guidance. You now get a clean message that includes your actual count and tells you exactly how many to remove (e.g. "You sent 20 reference images. Nano Banana supports up to 14 โ€” please remove 6 and try again.").

Cleaner Canvas Switches for WAN 2.5 and WAN Reference-to-Video

  • ๐ŸŽž๏ธ
    Fixed

    WAN 2.5 in Canvas no longer rejects 3s and 4s durations and now lets you go up to 15s. The duration slider used to span 3-10s, but the model's actual range is 5-15s, so picking 3 or 4 failed with "Number must be greater than or equal to 5" and the 11-15s range was hidden. Slider now matches the model exactly, and stale durations from sibling tools (WAN 2.2, Hailuo, LTX) auto-clamp into range.

  • ๐ŸŽฅ
    Fixed

    WAN Reference to Video in Canvas no longer fails when you switch in from a sibling tool with a different resolution or aspect-ratio picker. Stale '480p' values from WAN 2.2 and unsupported aspects like '3:2' used to slip through and trigger "Invalid enum value" โ€” Canvas now defensively falls back to 720p / 16:9 when an incompatible value is in flight.

P Video Avatar โ€” Talking Heads in 10 Languages

  • ๐Ÿ—ฃ๏ธ
    New

    P Video Avatar is live. Upload a portrait, write a short script (or paste an audio URL for lip-sync), and get a talking-head video. 30 named voices, 10 languages โ€” English (US/UK), Spanish, French, German, Italian, Portuguese, Japanese, Korean, Hindi. 1 credit per second at 720p, 2 credits per second at 1080p. Find it under Characters & Faces in the All Tools menu.

  • ๐Ÿ”ฅ
    New

    P Video Avatar runs unrestricted, so your spicy mode setting carries through the same way it does on the rest of the spicy-friendly tools.

Cleaner Canvas Switches for Hailuo 02, LTX 2, and Runway Gen-4.5

  • ๐ŸŽฌ
    Fixed

    Switching to Hailuo 02 in Canvas after a model with a different resolution picker (WAN 2.5, PixVerse, etc.) used to fail with "resolution: Invalid enum value, expected '768p' | '1080p', received '720p'" because Canvas carried over the previous model's value. Canvas now exposes Hailuo's exact resolutions and falls back to 768p when an incompatible value is in flight.

  • ๐ŸŽž๏ธ
    Fixed

    LTX 2 in Canvas no longer rejects odd-numbered durations. The duration slider used to step by 1 (so picking 7s or 11s failed with "Duration must be one of: 6, 8, 10, 12, 14, 16, 18, 20 seconds"); it's now an explicit list of valid lengths. Picking longer than 10s on the Fast tier also auto-locks 25fps + 1080p so the cross-tier requirement is always satisfied.

  • ๐ŸŽฅ
    Fixed

    Runway Gen-4.5 in Canvas now constrains duration to 5s or 10s the same way the standalone Runway Video tool does, so stale 6s/8s values from sibling models no longer leak through and fail with "duration: Invalid input".

Happy Horse Reference-to-Video + Video Edit Are Live

  • ๐ŸŽ
    New

    Happy Horse Reference to Video is here. Upload up to 9 reference images (characters, props, costumes), describe your scene with character1 / character2 tokens, and the model generates a video with each subject locked to its image. 720p or 1080p, 3-15 second clips, 4 credits per second at 720p and 6 at 1080p.

  • ๐Ÿช„
    New

    Happy Horse Video Edit lets you transform existing footage with a prompt โ€” style transfer ("make this look like a Studio Ghibli film") or local replacement ("swap the sweater for the one in the reference image"). Pair a source clip with up to 5 reference images, choose to keep your original audio or have new audio generated. Same pricing as the rest of the Happy Horse family โ€” 4 credits per output second at 720p, 6 at 1080p. Find both in Generate Videos under WAN Family.

Happy Horse 1.0 โ€” A New Video Model in the Lineup

  • ๐ŸŽ
    New

    Happy Horse 1.0 is now live. Generate fast, expressive video from text or a starting image at 720p or 1080p, with clip lengths from 2 to 15 seconds. 4 credits per second at 720p, 6 credits per second at 1080p. Find it under Generate Videos in the All Tools menu.

  • ๐Ÿ”ฅ
    New

    Happy Horse runs unrestricted out of the gate, alongside the rest of the spicy-friendly WAN family.

Qwen + Image-Relighting + Consistent Characters API Calls No Longer Hang

  • ๐Ÿ› ๏ธ
    Fixed

    Public API calls to qwen-image-2.0, qwen-image-2.0-pro, qwen-image (Plus/Max), the Qwen Image Edit model in image-relighting, and the Qwen Image 2 Pro model in consistent-characters were hanging indefinitely. The dashboard worked fine because it polls a different endpoint, but the public API's polling didn't recognize the internal job ids these tools were returning. They now return image URLs directly when called via the API โ€” first /api/v1/jobs/{id} GET serves the result. Dashboard / Canvas / Creator Studio behavior unchanged.

API Platform Now Auto-Tracks Every Tool, End to End

  • ๐Ÿ› ๏ธ
    New

    The Qwen Image Edit, Qwen Image 2 Edit, and HiDream Edit endpoints are now reachable via the public API at /api/v1/models/{qwen-image-edit, qwen-image-2-edit, hidream-edit}/run. Sister set to Generation now matches every dashboard tool 1:1 โ€” every customer-facing capability has a public apiId.

  • ๐Ÿ”—
    New

    Each /api-platform/{apiId} doc page now shows a "See also" section linking related apiIds (gen โ†” edit pairs across 16 tools: Flux, GPT Image, Nano Banana, Kling, P-Image, Qwen, Seedance, WAN, XAI, HiDream). Customers building integrations can discover companion endpoints without leaving the docs.

  • ๐ŸŽจ
    Improved

    Canvas's "More Settings" panel now auto-populates for any new tool โ€” derived from the tool's schema enums + inputParameters. Add a tool.config.ts and the tool gets a working settings panel for free, no manual registration in the Canvas params table.

  • ๐Ÿ›ก๏ธ
    New

    Two new CI gates so /api-platform docs and Canvas can't drift from the schemas: canvas-param-schemas-parity (every Canvas option must be schema-acceptable) and no-passthrough-schemas (schemas reject unknown fields, customers see clean 400s instead of silent drops).

  • ๐Ÿ“š
    Improved

    CLAUDE.md now formally documents the single-source-of-truth principle: tool.config.ts is canonical. Adding a tool means writing one file โ€” every doc surface, the public API, Canvas, Creator Studio, and OpenAPI all derive from it automatically.

Every Documented Enum Now Enforced By the API

  • ๐Ÿ› ๏ธ
    Fixed

    Closed the rest of the schema-vs-docs drift across the API platform: 11 more tools (Hailuo 02, Image Relighting, Pony XL, Qwen Image 2, Recraft, Seedream 4.5, Seedream 5 Lite, WAN 2.6 Image, WAN 2.6 Image Edit, WAN 2.7 Image, WAN 2.7 Image Edit) had documented enum lists for parameters like resolution, image_size, scheduler, output_format, and aspect_ratio while the schema accepted any string. The schema now enforces the same set the docs advertise โ€” bad values fail fast with a clear 400 instead of bouncing off the provider after credits are deducted.

  • ๐Ÿ›ก๏ธ
    Improved

    Added a reverse-direction parity check to CI (tests/contracts/tighten-loose-string-audit.test.ts): every documented enum value must be enforced by the schema. Combined with the existing forward check (every advertised value must be acceptable), the docs and schemas can't drift apart again.

API Aspect Ratios + Resolutions Now Match the Dashboard

  • ๐Ÿ› ๏ธ
    Fixed

    Aspect-ratio and resolution fields on the public API now reject invalid values up-front instead of being passed through to the provider for a confusing 422. ~16 tools (Flux, Flux 2, Flux Edit, Google Gemini Image, Nano Banana, Dreamina, Seedream 3, P-Image, P-Image Edit, Qwen Image, WAN 2.2 / 2.5 / 2.7 video, WAN Image, Ideogram Character, HiDream, Image Editor, Video Reframe, Video Transform, WAN 2.2 Animate) had loose `z.string()` validation that let unsupported values through silently โ€” they now use the same enum the dashboard offers.

  • ๐Ÿ“š
    Improved

    WAN 2.5 / 2.7 video API now accepts the documented `720p`/`1080p` form (the dashboard's value) โ€” previously the schema only accepted uppercase `720P`/`1080P` even though every doc said lowercase. The API now matches the docs and continues to send the upstream-correct uppercase form to DashScope on your behalf.

  • ๐Ÿ“š
    Improved

    HiDream resolution is now a proper enum on the API (`1024x1024`, `1360x768`, etc.). The dashboard's human-friendly form (`1024 ร— 1024 (Square)`) still works, so you can use either.

Smoother Canvas Chains + Friendlier Runware Errors

  • ๐ŸŽจ
    Fixed

    Runway Gen-4.5 was 500'ing on every Canvas chain because the duration picker emitted "5" or "10" as text but the schema expected a number. Both formats now work, so animating a Canvas frame with Runway goes through on the first try.

  • ๐ŸŽฌ
    Fixed

    LTX-2 was occasionally rejecting Canvas runs with "FPS must be one of: 24, 25, 48, 50" when the FPS dropdown was set โ€” same number-as-text mismatch. Coerced at the schema, so any FPS option you pick now works. Also added a guard that drops stale resolution values (like 480p left over from a previous WAN step) and falls back to 1080p instead of failing the run.

  • ๐Ÿ–ผ๏ธ
    Improved

    Consistent Characters and Google Nano Banana now show "Your reference image is outside the allowed size range. Please re-upload an image between 5KB and 20MB and try again." or "We couldn't fetch your reference image โ€” the link may be unreachable or the format unsupported. Please re-upload (JPEG or PNG) and try again." instead of a raw Runware JSON envelope with internal taskUUIDs and documentation URLs.

Image Editing Now Reachable via the Public API

  • ๐Ÿ› ๏ธ
    New

    Image-edit endpoints for GPT Image 2, GPT-Image 1.5, and OpenAI Image 1 are now available via the public API: POST /api/v1/models/gpt-image-2-edit/run, /gpt-image-1-5-edit/run, and /openai-image-1-edit/run. Send a prompt plus image_urls (or input_images) and the same edit pipeline the dashboard uses runs end-to-end โ€” image URL sanitization included. Existing /api/v1/models/{wan-2.7-image-edit, wan-2.6-image-edit, kling-image-edit, p-image-edit, xai-image-edit}/run already worked the same way; this fills in the orphans.

  • ๐Ÿ“š
    Improved

    Each new edit apiId is documented on /api-platform with example curls and shows up in /llm/{apiId}.txt for AI-assistant-driven integrations.

API Docs Parity: What You See Is What You Send

  • ๐Ÿ“š
    Fixed

    API documentation now matches the schemas the public API actually validates against. Previously several tools' /api-platform pages and /llm/{model}.txt docs advertised parameters the schema would silently drop โ€” for example `num_outputs` listed on Kling, Qwen, WAN, Seedream, Imagineart, P-Image, and others when the underlying schemas use `num_images`, `numberOfImages`, or `n` (or only generate one image per call). Renames + removals applied across ~15 tools so the names you read are the names the API accepts.

  • ๐Ÿ› ๏ธ
    Fixed

    Google Nano Banana 2 and Nano Banana Pro (text-to-image variants under /api/v1/models/google-gemini-image/run) advertised `reference_images` for guided generation but the schema didn't accept the field. Reference images now work end-to-end on those variants โ€” same image URL sanitization and Runware backbone the dashboard uses.

  • ๐Ÿ“š
    Improved

    /llm/{model}.txt now derives parameters from each tool's Zod schema when no hand-written list exists โ€” so reference-image fields, custom dimensions, and other inputs always show up in the LLM-friendly docs even for tools we haven't manually documented yet. Matches the same fallback /api/v1/models/{model} already does.

  • ๐Ÿ“
    Improved

    Heygen Avatar API parameters renamed to match the schema: `expression` โ†’ `expressionHappy`, `background.type` โ†’ `backgroundType`, `background.value` โ†’ `backgroundValue`. The dashboard already used these names; the API docs now agree.

  • ๐Ÿงน
    Fixed

    Deleted ~600 lines of stale hand-rolled API model entries that had drifted from each tool's actual schema (e.g. a static `nano-banana` apiId that competed with `google-nano-banana`, a `seedream-4` entry advertising `reference_images` while the live schema accepted `image_urls`). Every public apiId now comes from a single source of truth: the tool's own tool.config.ts.

Friendlier Errors For Unreadable + Unreachable Images

  • ๐Ÿ–ผ๏ธ
    Improved

    If you upload an unsupported image format (HEIC, AVIF) or a corrupted file to Seedream or Magnific, you now see "Could not read your reference image โ€” the file format may be unsupported (HEIC, AVIF) or the image may be corrupted. Please re-upload as JPEG or PNG." instead of a raw provider JSON dump or Python traceback.

  • ๐Ÿ”—
    Improved

    When a referenced image URL returns 404 / 403 / 401 (link expired or access denied), Grok Imagine Edit and other image-editing tools now say "We couldn't load your image โ€” the link returned 404 (not found). The image may have expired or moved. Please re-upload and try again." rather than "Failed to fetch image: 404".

  • ๐ŸŽจ
    Fixed

    Canvas was offering a 480p option for WAN 2.5 that the backend doesn't support (silently failed every run). Removed it from the Resolution dropdown. WAN 2.7 Video and Seedance 2 also now defensively normalize stale resolution values from previous Canvas steps so chains like "Kling Image โ†’ Seedance 2 video" no longer carry over the wrong setting.

  • ๐Ÿ”Œ
    Improved

    WAN family + Qwen models running on Alibaba DashScope now show "Alibaba DashScope is temporarily unreachable. Please try again in a moment." instead of a raw "fetch failed" error when the upstream service is briefly down. Same treatment for ByteDance / Seedream when its servers are overloaded โ€” credits are still refunded automatically.

  • ๐Ÿ› ๏ธ
    Fixed

    WAN 2.2 image-to-video was occasionally rejecting valid runs with "sample_shift: Must be greater than or equal to 1" from Replicate. The schema now bounds the field correctly and clamps any out-of-range value, so the run goes through cleanly.

Public API: Reference Images Now Actually Work

  • ๐Ÿ› ๏ธ
    Fixed

    Reference-image fields on public API endpoints (Nano Banana's image_input, Seedream's image_urls, Veo 3.1's reference_images, and every other tool that accepts source or reference URLs) were being silently dropped because the public API bypassed the per-tool payload shaping that tool pages, Canvas, and Creator Studio already used. Public API calls now run through the same submission pipeline โ€” including image URL sanitization, multi-tier routing (e.g. Veo 3.1 Lite correctly uses its own backbone), and field-name translation โ€” so a curl to /api/v1/models/{id}/run behaves identically to the same model on the site.

  • โšก
    Improved

    Synchronous image models (Seedream 4.5, Grok Imagine, Z-Image Turbo, Recraft sync, Nano Banana Pro) now return completed output on the first /api/v1/jobs/{id} poll โ€” no more spinning while waiting for a provider job that never existed.

LTX-2 API: Saner Defaults, Clearer Errors

  • ๐Ÿ› ๏ธ
    Fixed

    API calls to LTX-2 sub-models like /api/v1/models/ltx-2-pro-i2v/run were silently being validated as text-to-video instead of the mode the endpoint name implies, so callers got confusing errors about "text-to-video" rules while posting to an image-to-video endpoint. Each variant's mode is now applied automatically from the endpoint you call โ€” a minimal {prompt, image_url} call to ltx-2-pro-i2v just works.

  • ๐Ÿ’ฌ
    Improved

    LTX-2 fps validation used to return "fps: Invalid input" with no list of valid values. It now says "FPS must be one of: 24, 25, 48, 50." Aspect ratio errors similarly spell out the supported values and when each applies.

Community Gallery Is Now Members-Only

  • ๐Ÿ”’
    Improved

    The Community Gallery and user profile galleries are now behind sign-in. Browsing generations, exploring model pages, clicking into individual images, and viewing other creators' profiles all require a PixelDojo account going forward โ€” the same account you use for the dashboard. Signed-out visitors get bounced to sign-in and routed back to the page they wanted.

Video Upscaler + Video Transform Back To Working

  • ๐ŸŽฌ
    Fixed

    Video Upscaler and Video Transform were throwing "Prediction ID is missing in the response" on every submit after a recent behind-the-scenes change. Both tools are working again โ€” upload your clip and go.

  • ๐Ÿ’ฌ
    Improved

    If a P-API model (P-Image, P-Video) can't reach its upstream service, you now see "Pruna AI service is temporarily unreachable. Please try again in a moment." instead of the raw "fetch failed" error. Credits are still refunded automatically.

  • ๐ŸŽจ
    Fixed

    Canvas was failing silently on Flux Image-to-Image and Face Enhance when you tweaked More Settings like Guidance Scale, Prompt Strength, or Scale Factor โ€” the inputs emit text and the schema expected numbers. Both now accept either, so your Canvas runs go through on the first try.

  • ๐ŸŽจ
    Fixed

    Canvas was offering a 21:9 aspect ratio for Grok Imagine that the backend doesn't support, so that pick always 500'd. Canvas now only shows the 7 aspect ratios Grok actually accepts.

  • ๐Ÿ–ผ๏ธ
    Improved

    If you pick Flux Pro or Flux 1.1 Pro with 21:9 or 9:21, you now see "Flux 1.1 Pro does not support 21:9 โ€” try 16:9, or switch to Flux Schnell or Flux Dev for ultra-wide ratios." instead of a raw 422 dump from Replicate. No credits spent when the pre-check rejects.

  • ๐Ÿ”
    Fixed

    Creative Upscale was occasionally 500'ing from Canvas when Creativity or Resemblance sliders landed outside the provider's range. Values are now clamped to what Clarity Upscaler accepts (Creativity 0โ€“1, Resemblance 0โ€“3) so the run goes through cleanly.

Site-Wide Safety Hardening

  • ๐Ÿ›ก๏ธ
    New

    Prompt safety checks now run server-side on every tool, Canvas, Creator Studio, the public API, and LoRA training fields โ€” not just the dashboard pages that had the client-side check. Three layers: a public-figure name list, a deterministic phrase scanner, and an AI moderation backstop. Anything flagged returns a clear, actionable message about what to change.

  • ๐Ÿ›ก๏ธ
    Improved

    The image safety check that previously ran only on a couple of tools now applies to every tool that can produce explicit imagery, and uses a more reliable classifier than before. Photos that depict children are rejected with a specific message. Other tools (upscalers, background removers, analyzers) are unchanged.

  • ๐Ÿ›ก๏ธ
    New

    Every image stored on PixelDojo is now eligible for CSAM hash scanning at the storage layer. All upload paths โ€” generation outputs, reference images, and LoRA training datasets โ€” route through the same scanning coverage.

Friendlier Upload + Reference Image Errors

  • ๐Ÿ’ฌ
    Improved

    When an uploaded image is over our 12 MB cap, we now show your file's actual size and tell you to resize or compress โ€” no more guessing why the upload failed. Applies to every tool that takes an image.

  • ๐Ÿ’ฌ
    Improved

    On Seedream 4, if your reference image is bigger than the 36-megapixel limit or the host is slow to respond, you now get a clear message with the actual dimensions and next steps โ€” instead of a raw technical error.

Civitai.red Support For LoRA Imports

  • ๐Ÿงฉ
    Improved

    You can now paste Civitai model URLs from the new civitai.red domain anywhere we accept Civitai links โ€” LoRA training, model imports, and HuggingFace uploads all recognize it automatically.

Z Image Turbo Gets The Mobile Composer

  • โšก
    Improved

    Z Image Turbo โ€” the sub-second photorealistic model โ€” now has the sticky mobile composer. Describe, pick aspect ratio, add an optional LoRA, and generate up to four at a time. Eighteen tools on the new shell.

ImagineArt Joins The New Shell

  • ๐ŸŽจ
    Improved

    ImagineArt 1.5 now has the sticky mobile composer. Describe your image, pick aspect ratio and model tier, and generate up to four at a time from a single pull-up panel. Seventeen tools on the new shell.

Consistent Characters On The New Shell

  • ๐ŸŽญ
    Improved

    Portrait Series Generator (Consistent Characters) now has the sticky mobile composer. Pick a source portrait, choose a model, set a background, and generate up to 12 portraits โ€” all from a single pull-up panel. Sixteen tools on the new shell.

Three Audio/Video Tools Join The Shell

  • ๐ŸŽฌ
    Improved

    Lip Sync, Video Autocaption, and Video to Sound all got the sticky mobile composer. Fifteen tools on the new shell now. The interior UI on these three is still pre-design-system (custom headers and buttons) โ€” a polish pass will line them up with the rest.

Text To Music On The New Shell

  • ๐ŸŽต
    Improved

    Text To Music now has the sticky mobile composer. Describe the music, drag the length slider, tap an example prompt, generate โ€” all from a single pull-up panel. Eleven tools on the new shell.

Hunyuan 3D Gets The Mobile Composer

  • ๐ŸงŠ
    Improved

    Hunyuan 3D now has the sticky mobile composer. Pick text or image input, tweak advanced settings, and generate โ€” all from a single pull-up panel. Ten tools on the new shell.

Retired Three Orphan Tools

  • ๐Ÿงน
    Improved

    Subject Control, PuLID Characters, and Image to 3D have all been removed. Subject Control overlapped with Virtual Try-On and Style Transfer. PuLID and Image to 3D were both on disk but never made it into the sidebar menu โ€” nobody could navigate to them. Consistent Characters covers identity preservation, Hunyuan 3D covers 3D generation.

Dreamina in Canvas โ€” Only Valid Resolutions

  • ๐ŸŽจ
    Fixed

    Dreamina 3.1 in Canvas now only offers 1K and 2K for resolution โ€” the two values the model actually accepts. If your Canvas session had 4K or HD carried over from another model, Dreamina runs were failing at submit; stale state is now politely remapped to 2K instead of erroring.

Magic Lighting Gets The Mobile Composer

  • ๐Ÿ’ก
    Improved

    Magic Lighting now has the sticky mobile composer. Upload, pick a model, tap a lighting preset, and generate โ€” all from a single pull-up panel. Eight image tools on the new shell.

Style Transfer On The New Shell

  • ๐ŸŽจ
    Improved

    Style Transfer now has the sticky mobile composer. Source, style, prompt, and advanced settings all live in one pull-up panel. Seven image tools on the new shell now.

Change Camera Angle Gets The Mobile Composer

  • ๐Ÿ“ท
    Improved

    Change Camera Angle now has the sticky mobile composer. The orbit visualizer, sliders, presets, and generation options all live in one panel you can slide up from any scroll position. Six image tools on the new shell now.

Virtual Try-On Joins The New Shell

  • ๐Ÿ‘•
    Improved

    Virtual Try-On now has the sticky mobile composer. Upload your garment, pick your model, and generate from any scroll position โ€” five image tools on the new shell now.

Portrait Upscaler Gets The Mobile Composer

  • ๐Ÿ“ฑ
    Improved

    Portrait Upscaler now has the sticky mobile composer. Four image tools on the new shell so far โ€” upload, set your scale factor, and generate from any scroll position on mobile.

OmniHuman Audio Generation Fixed

  • ๐ŸŽ™๏ธ
    Fixed

    OmniHuman's 'Generate from Text' button works again. A plumbing change a week ago had disconnected the text-to-speech response from the page โ€” you'd click Generate Audio, nothing would appear, no error. Now it polls to completion and shows the audio ready to use. Caught while sweeping other tools for the same class of bug as Background Remover.

Background Remover Fixed + Two More Mobile Composers

  • ๐Ÿฉน
    Fixed

    Background Remover now actually shows your finished image again. A recent plumbing change had disconnected the final result from the page โ€” you'd click Remove Background, wait, and get sent back to the empty state with no image. Fixed, verified end-to-end.

  • ๐Ÿ“ฑ
    Improved

    Extract Frame and Image Analyzer now have the same sticky mobile composer as Background Remover. Tap the bar at the bottom to open controls, tap again to see your result. Three image tools on the new shell now; more following on the same cadence.

  • ๐Ÿ”’
    Improved

    Canvas signing now rotates on a 15-minute window, matching Creator Studio. If a signed link ever leaked from the page, its useful life is minutes, not hours. Zero visible change to how Canvas works for you.

Background Remover Gets A Mobile Composer

  • ๐Ÿ“ฑ
    Improved

    On mobile, Background Remover now has a sticky composer at the bottom of the screen โ€” tap to open the upload controls from any scroll position, tap again to collapse and see your result. Same pattern video tools have used for a while. First image tool to get it; the rest will follow.

  • ๐Ÿงน
    Improved

    Under the hood, image and video tools now share one shell. Three duplicate components (ToolWorkspaceShell, ToolPageHeader, ToolEmptyState) replace six parallel ones (VideoToolShell, VideoPageHeader, VideoEmptyState + image siblings). Every page you touch lives on the same plumbing now โ€” future polish lands everywhere at once.

Creator Studio Runs on the Same Rails

  • ๐ŸŽฌ
    Improved

    Every Creator Studio frame and video generation now flows through the same reliability backbone as tool pages and Canvas. If a model has an issue, we spot it and recover the same way whether you hit it from a tool page, Canvas, or Creator Studio. Zero visible change to your workflow โ€” just one shared plumbing instead of two.

One Design System, Edge to Edge

  • ๐ŸŸฃ
    Improved

    Flux LoRA trainers โ€” all six of them โ€” now use the proper Flux purple gradient on their Generate buttons and chrome. Orange-red and yellow-orange drifts are gone. Every Flux-family tool, training or generating, speaks the same color.

  • โœจ
    Improved

    Softer corners across marketing and landing pages โ€” hero cards, pricing tiles, community gallery, model showcases, and tutorial blocks now all share the same corner radius as the rest of the product. 42 files touched. The dashboard-to-landing transition is visibly one product now.

  • ๐ŸŽจ
    Improved

    Image tools and video tools now share one empty-state component. Video tools keep their icon pills and info tips (like "Lite supports 720p or 1080p in 16:9 and 9:16"), image tools keep their colored-dot pills, and the visual style is consistent across both. Under the hood this eliminated a whole duplicate component tree.

Purple Actually Looks Purple Now

  • ๐ŸŸฃ
    Fixed

    The shared component library had a longstanding bug where every 'purple' accent was silently rendering as sapphire (the primary brand color) instead of actual purple. Across the Flux family (Flux Studio, Flux 2 Flex, HiDream, PonyXL, LoRA Image Creator, Feedback) that meant empty states, prompt boxes, aspect ratio pickers, credit cost displays, and mode toggles were all speaking the wrong color. Fixed at the source โ€” 16 shared components across tool-components, video-components, history-grid, pricing-plans, admin, and my-images. Every purple-accented surface now renders actual purple.

Every Tool Wears The Right Family Color

  • ๐ŸŸก
    Improved

    Kling Image and Text to Music Generate buttons moved to amber โ€” the proper Kling-family and audio-category color. Matches the rest of the Kling and audio surfaces across the product.

  • ๐ŸŒน
    Improved

    xAI Image's Generate button cleaned up from a sapphire-to-rose mix to pure rose โ€” consistent with xAI Video and the rest of the xAI family.

  • ๐Ÿ”ต
    Improved

    Magnific Upscaler, Creative Upscale, and Google Gemini Image are now the category-correct blue on Generate and chrome, instead of sapphire, yellow-amber, or blue-purple mixes.

  • ๐Ÿฉต
    Improved

    Ernie and P-Image are now pure cyan โ€” matching Qwen, Recraft, ImagineArt, and the other cyan-family tools. No more stray rose or sapphire on their chrome.

  • ๐ŸŸฃ
    Improved

    LoRA Image Creator's cost display and Generate button are now the Flux-family purple gradient throughout instead of drifting back to sapphire.

  • ๐ŸŽซ
    Improved

    The Subscribe CTA on the Qwen Image 2 page moved from a mixed emerald-teal gradient to solid sapphire โ€” matching the product-wide rule that site-level actions like Subscribe are solid, while per-tool Generate buttons carry the gradient.

More Accurate Tool Colors

  • ๐ŸŸข
    Improved

    Video utility tools (Video Reframe, Video Transform, Video Upscaler, Lip Sync, Merge Videos) now share a consistent green across their Generate buttons and chrome โ€” matching the category identity.

  • ๐ŸŒน
    Improved

    Subject Control, a character tool, now uses rose โ€” the character-tool family color โ€” instead of sapphire.

  • ๐ŸŽจ
    Improved

    The Subscribe page CTA moved from a sapphire-to-blue gradient to solid sapphire โ€” site-level actions like Subscribe are solid sapphire across the product now, gradients are reserved for the single Generate button inside each tool.

Per-Family Colors Where They Belong

  • ๐ŸŸฃ
    Improved

    Flux 2 Flex and HiDream Generate buttons are now the same purple as Flux Studio and PonyXL โ€” matching the documented Flux-family color. Sub-states (editing, upload, etc.) all agree now instead of drifting between blue, sapphire, and green.

  • ๐ŸŸข
    Improved

    OpenAI Image 1's Generate button moved from a blue/sapphire gradient to emerald โ€” the proper OpenAI-family color, consistent with GPT Image 2 and GPT Image 1.5.

  • ๐ŸŸก
    Improved

    Video to Sound's Generate button now uses amber โ€” the audio-tool family color โ€” instead of blue. Matches Text to Music and other audio surfaces.

Subtle Studio Tune-up Across Tool Pages

  • โœจ
    Improved

    Softer corners on cards, sheets, and empty-state tiles across 17 tool pages โ€” from Flux Studio to Seedance 2 to Purchase Credits. The whole product sits at the same corner radius now instead of a handful of pages looking bubble-rounded.

  • ๐ŸŽจ
    Improved

    Flux Studio's Generate button now uses the proper Flux-family purple gradient instead of blue โ€” matches PonyXL and restores the family visual identity. The Subscribe-to-create CTA was cleaned up to solid sapphire (site-level actions are sapphire across the product now).

  • ๐Ÿ”‡
    Improved

    Removed a shimmer sweep animation from Generate buttons on Flux Studio and Seedream 4, plus the focus glow behind their prompt boxes. Tool surfaces are meant to be quiet; your prompt and your outputs hold focus now.

  • ๐Ÿ…ฐ๏ธ
    Improved

    Toned down all-caps-shouting button labels on Billing, Settings, My Prompts, Merge Videos, and Usage Report. Labels are readable at a glance now instead of broadcasting at you.

Creator Studio Feels Like One Studio

  • ๐ŸŽฌ
    Improved

    Creator Studio's chrome now matches the rest of PixelDojo. Buttons and labels across the project header โ€” Save, Characters, Scene, Shot Settings โ€” use the same quiet treatment you see on every tool page. Your project title reads in title case instead of all caps.

  • โœจ
    Improved

    Softer corners on the pre-project picker cards and the shot settings sheet. Same radius as the rest of the product, so Creator Studio sits next to Canvas and your tool pages without looking like a different app.

  • ๐ŸŽจ
    Improved

    The in-project workspace is calmer. Removed a decorative background glow so your storyboard holds focus. Ambient motion still lives on the pre-project picker where it belongs.

Seedance 2 โ€” New Backbone, Better Pricing

  • ๐ŸŽฌ
    Improved

    Seedance 2, Seedance 2 Reference, and Seedance 2 Video Edit have moved to a new backbone. Same models, faster and more reliable queuing โ€” no more jobs getting stuck on "queued."

  • ๐Ÿ’ณ
    Improved

    Most Seedance 2 generations now cost fewer credits. Fast 480p is down to 2 credits/sec and Fast 720p to 4 credits/sec. High 720p is 4 credits/sec (5 with a reference video), and High 1080p is 10 credits/sec (12 with a reference video). The quality popovers and Canvas cost displays reflect the new rates automatically.

  • ๐ŸŽž๏ธ
    Improved

    Seedance 2 Video Edit keeps Standard tier and full 480p / 720p / 1080p output; reference images and reference videos work the same way you're used to.

A Dashboard That Adapts To You

  • ๐Ÿ‘‹
    New

    Your dashboard now recognizes whether you've generated before. If you're a returning creator, the top of the page becomes a compact welcome strip with Create Image and Create Video ready to click โ€” and your Recent Creations move up to become the visual hero. First-time visitors still see the full onboarding intro so they know where to start.

  • ๐ŸŽจ
    Improved

    The home page buttons are now solid sapphire across the board โ€” no more yellow Buy Credits pill, no yellow hover flash on Create Image, no gradient Subscribe button. Cleaner, more consistent, and it lets your art stay the hero.

  • ๐Ÿท๏ธ
    Improved

    Featured Tools on the dashboard now show honest category labels โ€” Image, Video, Editing โ€” instead of marketing claims like "Best Quality" or "Most Flexible." You can see at a glance what each tool is for.

  • ๐ŸŽฌ
    New

    Video tutorials got their own home at /tutorials. The Master AI Creation video library moved off the main dashboard to a dedicated page, so your workspace stays focused on getting work done. You can jump to them anytime via the new Videos link in the Prompting Guides section.

  • โšก
    Improved

    The returning-visitor welcome strip keeps a Buy Credits (or Subscribe for free accounts) button right alongside Create Image and Create Video โ€” styled as a subtle sapphire-accented pill so it's always one click away without competing with your creative actions.

New GPT Image 2 Guide + Cohesive Guide Navigation

  • ๐Ÿ“˜
    New

    GPT Image 2 Prompting Guide is live at /guides/gpt-image-2-prompting-guide โ€” a hands-on playbook with seven generated examples covering near-perfect text rendering, dense infographic layouts, multilingual signage (Latin + CJK), world-aware photorealism, product mockups, character consistency, and UI mockups. Every prompt is copyable.

  • ๐Ÿงญ
    Improved

    Every prompting guide now has a clean breadcrumb trail โ€” Home โ€บ Prompting Guides โ€บ <Title> โ€” so you always know where you are and can jump back to the index with one click.

  • ๐Ÿ”—
    Improved

    The site footer has a new "Prompting Guides" column led by an "All Prompting Guides" link to the index, plus direct links to every major guide including GPT Image 2, Nano Banana Pro, Flux 2, Qwen Image 2, Seedream 5, Veo 3.1, Kling 3, and Seedance 2.

  • ๐Ÿ“š
    Improved

    The /guides index now lists every guide we've published โ€” including the WAN NSFW I2V guide under a new Adult (18+) category.

  • ๐Ÿ–ผ๏ธ
    Improved

    The AI Image landing page now leads with GPT Image 2 across its hero, FAQ, and structured data, and features a new Prompting Guides section so you can browse model-specific playbooks while choosing a generator.

Clearer Errors on Nano Banana Edit

  • ๐ŸŒ
    Fixed

    Uploading an unusually large reference image to Nano Banana Edit (Pro tier) used to return a raw provider JSON blob. You'll now get a short, actionable message telling you the image dimensions are outside the supported range and to resize to within 1โ€“12288 pixels per side before retrying.

GPT Image 2 โ€” 4K Rendering, Sharper Text

  • ๐Ÿ–ผ๏ธ
    New

    GPT Image 2 is live at /gpt-image-2 โ€” OpenAI's next-generation image model, with native 4K UHD rendering and noticeably sharper typography. Great for hero art, editorial covers, and print-ready marketing.

  • ๐Ÿ–ฅ๏ธ
    New

    Six explicit render sizes in the size picker: 1024ร—768, 1024ยฒ, 1024ร—1536, Full HD 1920ร—1080, QHD 2560ร—1440, and 4K UHD 3840ร—2160. Each 4K tile wears a small amber "2ร—" chip so you know when you're on the premium tier.

  • ๐Ÿ’ณ
    New

    Tiered credit pricing that tracks compute honestly. Low quality is a flat 0.5 credits per image at any size. Medium is 1.5 credits (3 at 4K UHD). High is 5 credits (10 at 4K UHD). The quality popover shows the live per-image cost for the size you picked, so there are no surprises.

  • ๐ŸŽจ
    New

    GPT Image 2 also supports edit workflows โ€” upload or pick reference images and describe your change. Multi-image refs, optional edit masks, and the same 4K rendering carry through.

  • ๐Ÿงฉ
    New

    Available in Canvas as a full generate step with size, quality, and format controls in More Settings, and exposed in the public API as the gpt-image-2 model ID.

Canvas Polish

  • ๐ŸŽฌ
    Fixed

    The Seedance 2 duration control in Canvas now shows the three durations the model actually supports โ€” 5s, 10s, 15s โ€” as discrete chips instead of a free-range slider. The slider let you pick 6 or 7 and then the model rejected the job; those nudges are no longer possible.

Ready for AI Agents

  • ๐Ÿค–
    New

    PixelDojo is now discoverable by AI agents and LLM-powered coding tools out of the box. The homepage and API reference advertise their machine-readable documentation (llms.txt, LLM-optimized reference, OpenAPI spec, ai-plugin manifest) through standard HTTP Link headers โ€” so agents like Claude Code, Cursor, and ChatGPT can find the API contract on first visit without any extra setup on your side.

  • ๐Ÿ“„
    New

    The API reference at /api-docs now speaks both HTML and Markdown from the same URL. Visit it in a browser and you get the rich HTML page; have an AI client fetch it with Accept: text/markdown and you get the LLM-optimized reference directly โ€” now with the correct text/markdown content type so strict agents accept it on first try.

  • ๐Ÿ“‡
    New

    Added an API catalog at /.well-known/api-catalog (RFC 9727) โ€” a single machine-readable index pointing to the OpenAPI spec, HTML and Markdown documentation, AI plugin manifest, and health endpoint. Agents that follow the well-known convention can now find everything they need in one request.

  • ๐Ÿงฐ
    New

    Published an Agent Skills index at /.well-known/agent-skills/index.json exposing three tool-worthy skills โ€” generate-image, generate-video, and list-models โ€” each backed by a markdown manifest with SHA-256 integrity. An agent runtime that speaks the Agent Skills Discovery RFC can now call PixelDojo image and video generation as first-class skills.

  • ๐Ÿ”‘
    New

    Added OAuth 2.0 Protected Resource Metadata at /.well-known/oauth-protected-resource (RFC 9728) with supported scopes and a pointer to the API key page. Agents can auto-discover how to get credentials for the PixelDojo API instead of needing bespoke setup docs.

  • ๐Ÿท๏ธ
    Improved

    Homepage structured data now identifies PixelDojo as a SoftwareApplication with a feature list, category, and offer details alongside the existing Organization and WebSite blocks. Cleaner ingestion by search engines and AI crawlers โ€” and more accurate knowledge cards in answers about what PixelDojo actually is.

  • ๐Ÿ›ก๏ธ
    Improved

    Declared our AI content preferences. The site robots.txt publishes Content Signals indicating the marketing site and documentation are open for AI training and inclusion in AI answers. User-generated gallery content and profile pages opt out of AI training via noai/noimageai โ€” your posted creations are crawled for search and inspiration, not harvested for training.

  • ๐Ÿชช
    New

    Agents can now auto-discover how to sign in. Added OpenID Connect discovery at /.well-known/openid-configuration and the matching OAuth 2.0 authorization server metadata at /.well-known/oauth-authorization-server, mirrored from our Clerk-backed auth. Agents that speak either flavor can find the issuer, endpoints, and supported scopes without any bespoke config.

  • ๐Ÿ“
    Improved

    Markdown negotiation now works site-wide on every agent-facing surface โ€” homepage, /agents, /api-platform, and /api-docs. Fetch any of them with Accept: text/markdown and you get the LLM-optimized reference; browsers keep getting the HTML pages. Moved the routing into middleware so it runs ahead of static-page caching, which the previous version got stuck behind.

  • ๐Ÿ”—
    Fixed

    Homepage Link headers are now served on every response, not just HTML ones. The original guard only emitted them when Accept: text/html was present, which meant agent crawlers using Accept: */* saw nothing. They now see the full RFC 8288 link graph (api-catalog, agent-skills, oauth-protected-resource, openid-configuration, service-doc, service-desc, and more) on any request to /.

Bulletproof Credits and API Keys

  • ๐Ÿ’ณ
    Improved

    Credit deductions are now fully transactional. Every debit and its ledger entry commit together as a single atomic unit, or not at all โ€” so even if the database blinks mid-generation, your balance and our record of where it went stay perfectly in sync. Eliminates a whole class of "my credits got deducted but the job never ran and I never got a refund" edge cases.

  • ๐Ÿ”
    Improved

    API keys are now stored as one-way hashes, not the raw key. The full secret lives only in your hands โ€” we cannot display it again after creation, and a database leak couldn't expose it either. Existing keys keep working seamlessly: they auto-upgrade to hashed storage the next time you use them. No rotation needed unless you've misplaced your copy.

  • ๐Ÿช
    Improved

    Webhook HMAC signatures now use a dedicated signing secret separate from your API key. The signing secret is generated per-key and kept isolated โ€” meaning webhook verification keeps working even if you rotate the API key, and vice versa.

Workspace Feel: Polished Cards, First-Run Delight, Editorial Changelog

  • ๐ŸŽจ
    Improved

    Tool pages feel more like a professional studio and less like a consumer toy. Image and video output cards have subtler shadows and a lighter hover lift, so the art stays the hero and the chrome gets out of the way.

  • โœจ
    New

    First-run delight: the first image, first video, and first Canvas chain step you generate in a session gets a small scale-in โ€” then the animation goes quiet so it doesn't fire on every click.

  • ๐Ÿ“ฐ
    Improved

    This page (What's New) got an editorial redesign. Bigger display headlines, typewriter-style dates, magazine spacing. Designed to be read, not skimmed.

Seedance 2 Reference & Video Edit: Updated Pricing

  • ๐Ÿ’ณ
    Improved

    Per-second credit pricing on Seedance 2 Reference to Video and Seedance 2 Video Edit has been adjusted to reflect their higher compute costs. Seedance 2 Reference: Fast 5 cr/s at 480p and 9.5 at 720p; High 8 at 480p, 16 at 720p, 24 at 1080p. Seedance 2 Video Edit: Fast 6.5 cr/s flat; Standard 5 at 480p, 9.5 at 720p, 16 at 1080p. Plain Seedance 2 (text/image-to-video) pricing is unchanged.

1080p on Seedance 2 + Standard Video Edit Back

  • ๐ŸŽฌ
    New

    1080p output is now available on Seedance 2, Seedance 2 Reference to Video, and Seedance 2 Video Edit โ€” on the High / Standard quality tiers. Fast tiers stay at 480p / 720p.

  • ๐ŸŽž๏ธ
    New

    Seedance 2 Video Edit brings back its Standard quality tier โ€” higher fidelity for prompted video edits, especially at 720p and 1080p.

  • ๐Ÿ’ณ
    Improved

    Pricing on all three Seedance 2 tools recalibrated to cleaner whole numbers. Seedance 2 / Reference: Fast 3 cr/s at 480p and 6 at 720p, High 5 at 480p, 10 at 720p, and 15 at 1080p. Seedance 2 Video Edit: Fast 4 cr/s flat; Standard 3 at 480p, 6 at 720p, 10 at 1080p.

  • ๐Ÿ› ๏ธ
    Fixed

    Seedance 2 generations no longer hang on "queued" forever after the backbone migration โ€” the status endpoint URL namespace was wrong in the first cut. New jobs now poll correctly.

  • ๐ŸŽž๏ธ
    Fixed

    Picking a video from "My Videos" in Seedance 2 Reference to Video no longer fails with "Failed to fetch" โ€” the library picker was re-validating CDN-hosted videos and tripping browser CORS. Library videos skip the re-fetch now (they were already validated at upload time).

Motion Preferences Respected

  • โ™ฟ
    Improved

    PixelDojo now respects your system-level "reduce motion" preference. If you have motion sensitivity settings turned on in your OS, decorative shimmer, pulse, and spin animations now pause, and transitions shorten. No setting to toggle in the app โ€” your OS choice just works everywhere.

Seedance 2 Tools Moved to a Faster Backbone

  • ๐ŸŽฌ
    Improved

    Seedance 2, Seedance 2 Reference to Video, and Seedance 2 Video Edit now run on a faster backbone โ€” same prompts, same credit prices, faster and more reliable queuing. Expect fewer stalled jobs during peak traffic.

Longer WAN 2.7 Video Prompts + Steadier Seedream 4

  • ๐Ÿ“
    Improved

    WAN 2.7 Video now accepts prompts up to 8,000 characters (previously 5,000). Long cinematic prompts and prompt-enhance expansions no longer trip the character cap.

  • ๐ŸŽฒ
    Fixed

    Seedream 4 now retries transient ByteDance "service encountered an unexpected internal error" responses automatically with backoff. Generations that would previously fail after a provider hiccup now recover on their own.

  • ๐Ÿ“
    Fixed

    Ideogram Character's resolution picker now lists only sizes the model actually accepts โ€” the old options (512ร—512, 768ร—768, 1280ร—720, 1920ร—1080, 1024ร—768, 768ร—1024) were silently rejected by Replicate. Replaced with nine provider-valid resolutions covering square, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, and ultra-wide/ultra-tall.

  • ๐ŸŽฅ
    Fixed

    Veo 3.1 Standard no longer offers 1:1 as an aspect ratio โ€” Google's API only accepts 16:9 and 9:16, so picking square was guaranteed to fail. The dropdown now matches what actually works.

  • ๐Ÿ“
    Improved

    Grok Image (xAI) now accepts prompts up to 5,000 characters (previously 2,000), matching P-Image, WAN 2.5, WAN 2.7 Video, and Seedance 2.

  • ๐ŸŽš๏ธ
    Fixed

    Canvas resolution picker for WAN 2.5, WAN 2.7 Video, and WAN Reference to Video now shows a proper 720p / 1080p chip selector instead of a free-text field โ€” no more "Expected '720P' received '720p'" surprises. Stale sessions with lowercase values still submit successfully.

  • ๐Ÿ“
    Improved

    Prompt length limits unified across every generation tool. Modern image and video models accept 65Kโ€“131K tokens (hundreds of thousands of characters), so our per-tool caps of 1Kโ€“8K chars have been lifted to a single generous 250K-character ceiling. Detailed multilingual prompts, prompt-enhance expansions, and long cinematic descriptions no longer hit arbitrary limits on Ernie, Kling, Grok, Hidream, FLUX Edit, WAN, Seedance, or any other tool.

Longer Prompts on P-Image Edit

  • ๐Ÿ“
    Improved

    P-Image Edit now accepts prompts up to 5,000 characters (previously capped at 2,000), matching its sibling P-Image tool. Detailed edit instructions and longer Canvas chains no longer hit a surprise validation error.

WAN 2.2 LoRA Support in the API

  • ๐ŸŽ›๏ธ
    Improved

    WAN 2.2's public API schema now documents all LoRA parameters. Standard mode supports two LoRAs (lora_weights_transformer + lora_weights_transformer_2 with matching scale fields), and Extended mode supports full dual-LoRA with four slots โ€” 1 and 3 target the high-noise transformer, 2 and 4 target the low-noise transformer. Scales accept 0โ€“4.

  • ๐Ÿ“
    Improved

    Seedance 2 now accepts prompts up to 5,000 characters (previously capped at 2,000), matching the longer-prompt tools like WAN 2.5 and WAN 2.7.

Accurate Pricing on Every Model

  • ๐Ÿ’ณ
    Fixed

    The API Platform pricing page now shows real credit costs for 17 more models that were stuck displaying "0 credits" โ€” Consistent Characters, FLUX, Flux Edit, Nano Banana Edit, Grok Imagine R2V, Ideogram Character, Kling Image V3, Kling Image Edit, Kling 2.6 Pro, Lip Sync, OmniHuman 1.5, Flux Redux, Seedance 1, Seedance 2 Reference, WAN 2.7 Image Edit, WAN Reference to Video, and WAN 2.7 Video Edit. Every variant now surfaces the correct per-request price.

Clearer Upload Errors

  • ๐Ÿ“ค
    Fixed

    When an image upload fails in an image-to-image tool or Canvas, you'll now see the real reason (like a session or subscription issue) instead of a generic "Failed to upload" message that made it look like the file itself was the problem.

Seedance 2 Reference to Video

  • ๐ŸŽฌ
    New

    Seedance 2 Reference to Video is live. Guide Seedance 2.0 with up to 9 reference images, 3 video clips, and 3 audio tracks โ€” tag them in your prompt as [Image1], [Video1], [Audio1] to lock characters, motion, and sound in a single generation. Fast (3/5 credits/sec at 480p/720p) and High (3/6 credits/sec) tiers, native audio sync, 3โ€“15 second clips.

  • ๐ŸŽ›๏ธ
    Improved

    Seedance 2 Reference in Canvas now shows proper Quality, Resolution, Duration, Aspect Ratio, and Generate Audio dropdowns instead of raw text inputs that could silently fail validation.

  • ๐Ÿ“
    Improved

    P-Image, WAN 2.5, and WAN 2.7 Video now accept longer prompts (up to 5,000 characters) โ€” previously anything over 2,000 characters was rejected with a validation error.

Canvas Settings Polished for New Tools

  • ๐ŸŽ›๏ธ
    Improved

    GPT-Image 1.5, Qwen Image 2, and Ideogram Character now show proper dropdowns in Canvas More Settings โ€” Size, Quality, Model, Speed, and Style controls replace raw text fields that sometimes caused silent failures.

  • ๐Ÿ–ผ๏ธ
    Fixed

    Seedream 4 edit mode no longer rejects requests that pass a single reference URL instead of an array โ€” the API now accepts both forms gracefully.

  • ๐ŸŽญ
    Fixed

    Pose Control (FLUX) works again โ€” submissions without a LoRA were being rejected upstream because the empty strength value was sent as a string instead of a number.

  • ๐ŸŽฌ
    Improved

    Grok Imagine Video in Canvas now has proper Duration, Resolution, and Aspect Ratio dropdowns instead of raw text fields that silently failed validation.

  • ๐Ÿ›ก๏ธ
    Improved

    Earlier validation on Veo 3.1, WAN 2.6 Image Edit, and Seedream edit. Veo 3.1 (standard) now catches 1:1 aspect ratio with an input image upfront and asks for 16:9 or 9:16. WAN 2.6 Image Edit caps reference images at 4 when selecting. Seedream 4 and Seedream 5 Lite edit cap reference images at 14 when selecting. All three avoid confusing post-submit errors.

Canvas Continuity + Broken Tools Unbroken

  • ๐Ÿ”ฅ
    New

    Ernie โ€” Baidu's multilingual text-to-image model is live. Write prompts in English, Chinese, or Japanese with built-in prompt expansion. HD is 1 credit, UHD is 3 credits, and the Turbo variant is 1 credit flat.

  • ๐ŸŽจ
    Fixed

    "Continue in Canvas" actually sends your image into Canvas now. If you'd ever used Canvas before, the button used to take you there empty-handed.

  • ๐Ÿ–ผ๏ธ
    Fixed

    Seedream 4 and Seedream 5 Lite edit mode accept pasted or newly-uploaded images again โ€” base64 uploads were timing out before reaching the backend.

  • ๐ŸŽฌ
    Fixed

    Veo 3.1 Lite videos finish and display correctly. Jobs were completing on the provider but never got picked up on our side.

  • ๐ŸŽญ
    Fixed

    Pose Control (FLUX) with multiple LoRAs works now โ€” was 0% success after the multi-LoRA update.

  • โœ‚๏ธ
    Fixed

    SeedEdit 3 is back online after a provider API change broke every request.

  • ๐ŸŽž๏ธ
    Improved

    LTX 2 in Canvas now has proper Tier, Duration, Resolution, and FPS dropdowns instead of raw text inputs.

  • ๐ŸŽฌ
    Improved

    WAN Reference to Video in Canvas gets proper Duration slider plus Resolution, Aspect Ratio, Model, and Shot Type dropdowns โ€” no more typing values that silently fail.

  • ๐Ÿ–Œ๏ธ
    Improved

    WAN 2.6 Image Edit in Canvas now has Size, Prompt Enhancement, and Negative Prompt as proper form controls. Previously free-text fields were tripping validation.

  • ๐Ÿ”
    Improved

    Magnific Upscaler now catches oversized images upfront with a clear "Image is too large to upscale (max 10 MB)" message instead of a cryptic upstream error.

  • ๐ŸŒ
    Fixed

    Nano Banana edits with "Match input image" aspect ratio no longer 400 on the upstream API โ€” always sends explicit width and height now.

  • ๐ŸŽฅ
    Fixed

    Seedance 2 image-to-video no longer complains that you need an image after you already uploaded one โ€” mode and image state stay in sync.

  • ๐ŸŽ™๏ธ
    Fixed

    Omnihuman's Fearful, Disgusted, and Surprised emotions produce audio now (were sending wrong values to the voice engine).

  • โœจ
    Improved

    Flux Edit's guidance slider in Canvas now stays inside the range the model accepts โ€” no more mid-drag validation errors.

  • โŒจ๏ธ
    Improved

    Empty-prompt submissions across 30+ tools now show a clean error. Advanced JSON mode, Enter-key submits, and rapid clicks all get caught client-side instead of hitting the API.

  • ๐Ÿ“Š
    Improved

    Content-moderation rejections across the Seedream and Seedance families are correctly labeled as content issues instead of provider outages โ€” cleaner signal when something is actually broken.

  • ๐Ÿ”Œ
    Fixed

    Public API calls to Heygen Avatar, Flux variants, Kling, Veo, Seedream, Seedance, WAN, Recraft, Ernie, and ~60 other models no longer return a spurious "Invalid credit amount" error. Per-request pricing for these models now flows through to the API correctly.

  • ๐Ÿ’ณ
    Fixed

    The /api/v1/models listing and API Platform docs pages show real credit costs for dynamically-priced models instead of "0 credits".

  • โšก
    Improved

    Your Usage report loads noticeably faster โ€” added indexes that make per-user lookups across credits and refunds much quicker, especially for longer time ranges.

Smarter Canvas + Fewer Bugs Everywhere

  • ๐ŸŽจ
    Improved

    Canvas's model picker now shows every model tier as its own option โ€” pick Nano Banana Standard, Pro, or 2 directly instead of hunting through settings.

  • ๐Ÿ–ผ๏ธ
    New

    Multi-image editing in Canvas โ€” models like Nano Banana Edit, P-Image Edit, and WAN 2.6 Image Edit accept up to 5 reference images. Click '+ Add reference' next to your source to attach more.

  • โš™๏ธ
    Improved

    Canvas's More Settings panel is way friendlier. Aspect ratio and resolution are dropdowns. Image slots have a proper picker. Fields you've already filled from a canvas step get hidden so you're not duplicating work.

  • ๐ŸŽฌ
    Improved

    When you pick an image source for a video tool, mode auto-flips to image-to-video and the image slot is pre-filled. No more empty fields asking what to do.

  • โœจ
    New

    P-Image Edit is now available in both the public API and Canvas โ€” fast image editing with up to 5 reference images.

  • ๐Ÿ”ง
    Fixed

    Fixed the bug that silently sent edits to the wrong endpoint โ€” Canvas edits now land on the correct model every time.

  • ๐Ÿ“Š
    New

    Admin Tool Health dashboard โ€” per-tool success rate, error breakdown, and latency for the last 7 days.

  • ๐ŸŒž
    Fixed

    Light mode contrast fixes on the Canvas source indicator and temporary-output warning โ€” readable in both themes now.

  • ๐ŸŽฌ
    Fixed

    WAN 2.5 Image-to-Video now disables Generate until you've uploaded an image โ€” no more silent failures.

  • ๐ŸŽž๏ธ
    Fixed

    WAN 2.7 Video Extend mode waits for your source clip's duration to finish processing before letting you Generate.

  • ๐ŸŒ
    Fixed

    Nano Banana Pro and Nano Banana 2 work correctly via the public API again โ€” requests now route to the right backend.

WAN 2.7 Image Editing & Usage Insights

  • ๐Ÿ–Œ๏ธ
    New

    Image editing tools added to WAN 2.7 โ€” paint over areas and regenerate with AI.

  • ๐Ÿ“Š
    New

    Usage history now shows which tool and provider were used for each generation.

  • โšก
    Improved

    All API error messages are now clearer and more consistent across every endpoint.

Security Hardening & Performance Boost

  • ๐Ÿ”’
    Improved

    Strengthened security across the platform โ€” all endpoints now require proper authentication.

  • ๐Ÿš€
    Improved

    Homepage loads 40% faster. Font loading improved by 97%.

  • ๐Ÿงน
    Improved

    Removed 90+ unused files and 48 unnecessary dependencies for a leaner, faster app.

Smarter Credit Management

  • ๐Ÿ’ณ
    Improved

    Credits are now deducted upfront for LoRA training jobs โ€” no more surprise charges.

  • ๐Ÿ”„
    Improved

    Automatic refunds are more reliable โ€” failed jobs always return your credits.

Fresh Design System

  • ๐ŸŽจ
    New

    Brand-new Sapphire color scheme across the entire platform for a cleaner, more modern look.

  • โœจ
    Improved

    Updated accent colors for each tool family โ€” image, video, and editing tools now have distinct visual identities.

  • ๐Ÿ”ค
    Improved

    New typography with Satoshi for headlines and Geist for body text โ€” easier to read everywhere.

Refund System Overhaul

  • ๐Ÿ’ฐ
    New

    Credit refunds section added to your usage report so you can track every refund.

  • ๐Ÿ›ก๏ธ
    Improved

    Refund tracking is now more transparent โ€” see exactly when and why credits were returned.

  • ๐Ÿ”ง
    Fixed

    Resolved edge cases where timed-out jobs weren't automatically refunding credits.

Job Reconciliation & Admin Tools

  • โฑ๏ธ
    New

    Stuck jobs are now automatically detected and refunded every 10 minutes.

  • ๐ŸŽ›๏ธ
    Improved

    Admin dashboard now has better tools for monitoring job health across the platform.

WAN 2.7 Video & Image Generation

  • ๐ŸŽฌ
    New

    WAN 2.7 Video is here โ€” next-generation video creation with improved motion and detail.

  • ๐Ÿ–ผ๏ธ
    New

    WAN 2.7 Image generation added with updated model configurations.

  • ๐Ÿ”—
    New

    Video continuation support โ€” extend your WAN 2.7 videos with last-frame extraction.

  • ๐Ÿ“
    Improved

    Better resolution handling for video models with smarter aspect ratio defaults.

Payment Flow & Purchase Credits

  • ๐Ÿ’ณ
    Improved

    Streamlined credit purchase flow โ€” fewer steps to top up your account.

  • ๐Ÿงพ
    Improved

    Better error messages during checkout so you always know what happened.

WAN 2.6 & Reference-to-Video

  • ๐ŸŽž๏ธ
    New

    WAN 2.6 Image model added to the lineup.

  • ๐Ÿ“ธ
    Improved

    Reference-to-video now supports WAN 2.7 with better subject consistency.

  • ๐Ÿ”
    New

    Auto-resubmit for failed video downloads โ€” no more lost generations.

Creator Studio Upgrades

  • ๐ŸŽฏ
    Improved

    Prompt enhancement defaults updated for QWEN Image 2 and Flux 2 for better results out of the box.

  • ๐Ÿ‘ค
    Improved

    HeyGen avatar tool now has smarter credit calculations based on video length.

Seedance 2 & New Models

  • ๐Ÿ’ƒ
    New

    Seedance 2 is live โ€” create videos with realistic motion and native audio awareness.

  • ๐Ÿค–
    New

    Updated AI model roster with the latest versions and pricing.

  • ๐Ÿ“
    New

    Video prompting guides added to the homepage for quick access.

Seedream 4 & Mobile Improvements

  • ๐ŸŒŸ
    New

    Seedream 4 now supports custom image sizes and aspect ratio selection.

  • ๐Ÿ“ฑ
    New

    Sticky composer toggle makes it easier to create on mobile devices.

  • ๐Ÿ“Š
    Improved

    Funnel analytics now include date range selection and device breakdown.

API Platform & Developer Docs

  • ๐Ÿ“š
    New

    Expanded API documentation with model discovery and job control endpoints.

  • ๐Ÿ”
    New

    AI agent discovery endpoint added โ€” build smarter integrations with PixelDojo.

  • ๐Ÿ’ฐ
    Improved

    API credit costs now adjust based on resolution for fairer pricing.

LTX 2.3 & Kling v3

  • ๐ŸŽฌ
    New

    LTX 2.3 video model with revised pricing and UI improvements.

  • ๐ŸŽฅ
    New

    Kling Video upgraded to v3 with updated credit pricing and new motion controls.

  • ๐Ÿ’ต
    Improved

    Better subscription management โ€” cancel at period end without losing remaining access.

Pruna AI & Better Video Tools

  • โšก
    New

    Pruna AI integration for faster image and video generation.

  • ๐ŸŽž๏ธ
    New

    Extended quality mode for WAN 2.2 video โ€” longer, higher-quality outputs.

  • ๐ŸŽจ
    Improved

    LoRA support added to WAN 2.2 for custom-trained style videos.

Runway Video & Text-to-Music

  • ๐Ÿƒ
    New

    Runway Video generation is now available with the latest model.

  • ๐ŸŽต
    Improved

    Text-to-music pricing updated with better form validation for smoother creation.

  • ๐Ÿ”ง
    Fixed

    Improved error handling across video and image generation endpoints.

Nano Banana Pro (Fast Backbone)

  • ๐ŸŒ
    New

    Nano Banana Pro image generation on a faster backbone for blazing-fast results.

  • ๐ŸŽญ
    New

    Consistent character generation now works with Nano Banana 2 models.

  • โšก
    Improved

    Smarter error messages with friendly descriptions when something goes wrong.

Creator Studio Storyboards

  • ๐Ÿ“–
    New

    Storyboard export with transition controls โ€” plan your video projects visually.

  • ๐ŸŽฌ
    New

    Per-clip audio controls in the video merger tool.

  • ๐Ÿค–
    New

    Choose your LLM model for storyboard generation.

Nano Banana 2 & Seedream 5 Lite

  • ๐ŸŒ
    New

    Nano Banana 2 models added with updated configurations across all tools.

  • ๐ŸŒŸ
    New

    Seedream 5 Lite and Seedream 5 Lite Edit models are now available.

  • ๐Ÿ“š
    New

    New prompting guides added for popular models.

QWEN Image 2 & xAI Tools

  • ๐Ÿ–ผ๏ธ
    New

    QWEN Image 2 model with smart aspect ratio and resolution tier selection.

  • ๐Ÿค–
    New

    xAI video and image tools now available.

  • ๐ŸŒฑ
    Improved

    Flux seed management for reproducible image generation โ€” get the same result every time.

Referral Program & Attribution

  • ๐ŸŽ
    New

    Referral tracking is live โ€” earn 100 credits for every friend you invite.

  • ๐Ÿ“ˆ
    New

    Attribution touch tracking for better understanding of how users find PixelDojo.

Email Notifications & Admin Dashboard

  • ๐Ÿ“ง
    New

    SendGrid email lifecycle integration for account notifications.

  • ๐Ÿง 
    New

    AI-powered overview and funnel insights added to the admin dashboard.

  • ๐Ÿ“Š
    New

    Funnel analytics with period selection and device breakdown.

Flux 2 Flex & Kling Image

  • ๐ŸŽจ
    New

    Flux 2 Klein 9B model added with updated credit costs and parameters.

  • ๐Ÿ–ผ๏ธ
    New

    Kling Image model now available for high-quality AI image generation.

  • โœ๏ธ
    Improved

    Flux edit mode upgraded for faster, more iterative image refinement.

Seedance End Frames & SEO Improvements

  • ๐ŸŽฌ
    New

    Optional end frames in Seedance video generation for more control over your clips.

  • ๐Ÿ”
    Improved

    Better SEO across all category pages with video support and improved metadata.

  • ๐Ÿ“
    Improved

    Smarter aspect ratio handling across all generation tools.

Prompting Guides Hub

  • ๐Ÿ“š
    New

    Video prompting guide with shot structure, camera language, and prompt templates.

  • ๐Ÿ“–
    New

    Nano Banana Pro prompting guide with comparison examples and best practices.

  • ๐Ÿ 
    New

    Prompting guides section added directly to the dashboard homepage.

Hailuo 2.3 & Sora 2 Reference Images

  • ๐ŸŽฌ
    Improved

    Hailuo video model upgraded to v2.3 with better motion quality.

  • ๐Ÿ“ธ
    New

    Sora 2 now supports reference images โ€” guide your video generations with a starting photo.

  • ๐Ÿ–ผ๏ธ
    Improved

    Faster image loading across the platform with optimized loaders.

Seedance 1 & LTX-2 Video

  • ๐Ÿ’ƒ
    New

    Seedance 1 video model with updated pricing and generation options.

  • ๐ŸŽฅ
    New

    LTX-2 video model added to the platform.

  • ๐Ÿ’ฐ
    New

    Automatic credit refunds for failed LTX-2 video generations.

Prompt Enhancement & Image Moderation

  • โœจ
    New

    One-click prompt enhancement โ€” improve your prompts with AI before generating.

  • ๐Ÿ›ก๏ธ
    New

    Image moderation for uploads to keep the community safe.

  • ๐Ÿ“
    Improved

    Optional prompt field added to more tools for greater creative control.

Cancellation Flow & Policy Updates

  • ๐Ÿ“‹
    Improved

    Smoother cancellation experience with clear feedback and options.

  • ๐Ÿ“„
    Improved

    Updated privacy policy and terms of service with clearer language.

  • ๐Ÿ”’
    Improved

    Enhanced content safety policies across the platform.

Seedream 4.5 & Image Relighting

  • ๐ŸŒŸ
    Improved

    Seedream upgraded to 4.5 with enhanced features and better output quality.

  • ๐Ÿ’ก
    New

    Image relighting tool โ€” change the lighting in any image with AI.

  • ๐ŸŽญ
    Improved

    Consistent character generation with better prompt handling and job management.

Creator Studio Launch

  • ๐ŸŽฌ
    New

    Creator Studio is here โ€” plan and produce multi-scene video projects with storyboards.

  • ๐ŸŽจ
    New

    Multiple video and image model options inside Creator Studio.

  • ๐Ÿ“
    New

    Media folder management and project organization built in.

  • ๐Ÿ‘ค
    New

    Character attribute editor for consistent characters across scenes.

Consistent Characters & Flux 2 Dev

  • ๐Ÿ‘ฅ
    New

    Consistent character generation โ€” keep the same character across multiple images.

  • ๐ŸŽจ
    New

    Flux 2 Dev model support added for consistent character workflows.

  • ๐Ÿ’พ
    New

    Save generated assets directly to CDN from Creator Studio.

Z-Image Turbo & LoRA Training Upgrades

  • โšก
    New

    Z-Image Turbo for ultra-fast image generation with LoRA support.

  • ๐Ÿง 
    Improved

    LoRA training forms upgraded with better FAQs and multi-image upload support.

  • ๐Ÿ“ฆ
    New

    Zip file upload for LoRA training โ€” upload all your training images at once.

Seedream 4 Image Editing

  • โœ๏ธ
    New

    Seedream 4 edit endpoint โ€” modify existing images with AI-powered editing.

  • ๐Ÿ–ผ๏ธ
    New

    Multi-image blending in Seedream 4 for creative composites.

  • ๐Ÿ”„
    New

    Retry logic for more reliable generations on Gemini and other models.

Dashboard Redesign

  • ๐Ÿ 
    Improved

    Redesigned dashboard homepage with recent creations and featured tools front and center.

  • โญ
    New

    Favorites โ€” save your best images and videos for quick access.

  • ๐ŸŽจ
    Improved

    Refreshed button styles and tooltips across all tools for a more polished look.

Flux 2 Flex & Google Gemini Image

  • ๐ŸŽจ
    New

    Flux 2 Flex with Klein 4B model support and improved documentation.

  • ๐Ÿค–
    New

    Google Gemini Image generation with enhanced job tracking.

  • ๐Ÿ“
    Improved

    Better credit cost calculations with per-model pricing.

WAN 2.2 Plus Mode & Frame Extraction

  • ๐ŸŽฌ
    New

    WAN 2.2 Plus mode for higher quality video output.

  • ๐Ÿ–ผ๏ธ
    New

    Frame extraction tool โ€” pull still frames from any video.

  • ๐Ÿ”„
    New

    Interpolation output option for smoother WAN 2.2 videos.

API Platform & Model Registry

  • ๐Ÿ“š
    New

    Expanded API platform with comprehensive model registry and documentation.

  • ๐Ÿ”‘
    New

    API key management with subscription and rate limit checks.

  • ๐Ÿ’ฌ
    New

    In-app FAQ system with searchable help articles.

Kling 2.6 Pro & Creator Studio Video

  • ๐ŸŽฅ
    New

    Kling 2.6 Pro video model now available in Creator Studio.

  • ๐Ÿ“ธ
    New

    Image source picker for video generation โ€” start from any image.

  • ๐Ÿ’ฐ
    Improved

    Smarter credit calculations across all video models.

New Models & Enhanced Admin

  • ๐Ÿค–
    New

    Multiple new AI models added with competitive pricing.

  • ๐Ÿ”ง
    Improved

    Admin dashboard with better user data display and management tools.

  • ๐Ÿ“Š
    Improved

    Enhanced subscription handling and billing cycle management.

Automated News & Flux Updates

  • ๐Ÿ“ฐ
    New

    Automated news publishing โ€” platform updates now post automatically.

  • ๐ŸŽจ
    New

    New Flux models with enhanced credit management.

  • โฌ†๏ธ
    New

    Magnific upscaler with improved credit cost calculations.

WAN 2.5 & Video Caching

  • ๐ŸŽฌ
    New

    WAN 2.5 video generation with image-to-video and text-to-video modes.

  • ๐ŸŽต
    New

    Audio URL support in WAN 2.5 for video-with-sound generation.

  • โšก
    Improved

    Video caching to R2 for faster replay of generated videos.

Face Swap & WAN 2.6 Image Editing

  • ๐ŸŽญ
    New

    Face swap tool โ€” swap faces in any image with AI.

  • โœ๏ธ
    New

    WAN 2.6 Image editing with output size controls.

  • ๐Ÿ”„
    New

    Use Previous Frame feature in Creator Studio for seamless video continuity.

Multi-Select & Batch Actions

  • โ˜‘๏ธ
    New

    Select multiple images or videos at once for batch actions.

  • ๐Ÿ“ค
    New

    Batch download, delete, and organize your generations.

  • ๐Ÿ“ฑ
    Improved

    Better mobile responsiveness across all generation tools.

LTX-2 Duration Options & Video Merge

  • โฑ๏ธ
    New

    Custom duration options for LTX-2 video generation.

  • ๐ŸŽฌ
    Improved

    Video merge tool with better upload support.

  • ๐Ÿ”
    Improved

    Enhanced image display and layout consistency across all tools.

Usage Reports & Image Validation

  • ๐Ÿ“Š
    Improved

    Redesigned usage report page with sorting and better UI.

  • ๐Ÿ–ผ๏ธ
    Improved

    Centralized image validation for more consistent uploads across all tools.

  • ๐ŸŽฅ
    Improved

    Better video history layout with improved responsiveness.

Veo 3.1 & Reality Polisher

  • ๐ŸŽฌ
    New

    Veo 3.1 video generation with premium cinematic controls.

  • ๐Ÿ”
    New

    Reality Polisher โ€” detect and fix AI artifacts in generated images.

  • ๐Ÿท๏ธ
    Improved

    Model visibility toggle for the community gallery.

ImagineArt & Featured Tools

  • ๐ŸŽจ
    New

    ImagineArt model with multiple output count options.

  • ๐ŸŒŸ
    Improved

    Updated featured tools on the homepage with fresh highlights.

  • ๐Ÿ“ฑ
    Improved

    Better layout responsiveness across Creator Studio and dashboard.

Whop Payments & Subscription Upgrade

  • ๐Ÿ’ณ
    New

    New payment provider for smoother subscription management.

  • ๐Ÿ”„
    Improved

    More reliable webhook handling for subscription changes.

  • ๐Ÿ“ฆ
    Improved

    Credit pack purchases now process faster and more reliably.

Authorize.Net & Split Payments

  • ๐Ÿ’ณ
    New

    Authorize.Net integration for credit card top-ups.

  • ๐Ÿ”€
    New

    Split-provider payment flow โ€” choose your preferred payment method.

  • ๐ŸŽฌ
    Improved

    AutoPlay video showcase on the landing page with deferred loading for faster page loads.

Seedance 1.5 & Prompt Manager

  • ๐Ÿ’ƒ
    Improved

    Seedance upgraded to 1.5 with better pricing and documentation.

  • ๐Ÿ“
    Improved

    Prompt manager with search and dynamic loading for faster prompt browsing.

  • ๐Ÿงญ
    Improved

    Streamlined dashboard navigation and optimized training data handling.

New AI Image Editing & LoRA Image Creator

  • ๐ŸŽจ
    New

    New AI-powered image editing tools.

  • ๐Ÿ–ผ๏ธ
    Improved

    LoRA Image Creator with modal selection and better model version handling.

  • ๐Ÿ“Š
    Improved

    Google Gemini Image with better job tracking and filtering.

Cost Comparison & Landing Page Refresh

  • ๐Ÿ’ฐ
    New

    Cost comparison tool on the landing page โ€” see how PixelDojo pricing stacks up.

  • ๐Ÿ 
    Improved

    Refreshed landing page with Flux 2 features and better model showcases.

  • ๐ŸŽฏ
    Improved

    Updated credit cost structure for Flux models.