# PixelDojo

> AI image and video generation platform with a REST API.

## Pricing

- Bigger plans get cheaper credits: Lite $10/month for 160 credits (6.25¢ each), Pro $25/month for 500 credits (5¢ each), Pro Max $50/month for 1,100 credits (4.55¢ each).
- Prepaid terms, credits every month: 6 months of Pro for $135 (500 credits a month, 4.5¢ each) or a year of Pro Max for $570 (1,100 credits a month, 4.32¢ each).
- Credit packs: $5 to $100 at 6.25¢ per credit; $250 for 4,400 credits (5.69¢ each); $500 for 9,000 credits (5.56¢ each, subscribers only).

## API

PixelDojo provides an async job-based API for programmatic access to AI image and video generation models.

- Base URL: https://pixeldojo.ai/api/v1
- Auth: Bearer token (API key)
- Endpoint: POST /models/{modelId}/run → GET /jobs/{jobId}
- Models available: 150

### Available Models
  - bria-3-2: Bria 3.2: text-to-image with 9 aspect ratio presets at 1K resolution, optional image and prompt enhancement, and photography/art medium hints. (1 credit(s))
  - change-camera-angle: Camera-aware editing via Qwen Image Edit with multi-angle LoRA. 360° orbit, tilt, and zoom. (1 credit(s))
  - clarity-pro-upscaler: Clarity Pro Upscaler. Photorealistic upscaling with identity preservation and creative control: up to 16× and 64 megapixels. (4 credit(s))
  - consistent-characters: Generate consistent character variations with FLUX Kontext, Nano Banana Pro/2, Flux 2 Dev, Qwen Image 2 Pro, or Grok Imagine. (1.25 credit(s))
  - creative-upscale: Clarity Upscaler (creative upscale). Boost detail with stable-diffusion refinement. (2.5 credit(s))
  - ernie: Baidu Ernie text-to-image. Multilingual prompts and built-in prompt expansion. (1 credit(s))
  - face-enhance: Crystal Upscaler. Face-detail preserving upscale, cost scales with output megapixels. (6 credit(s))
  - flux: FLUX family. Schnell, Dev, Pro, Kontext, Ultra, and LoRA remix variants in one entrypoint. (1 credit(s))
  - flux-2-flex: Max-quality with up to 10 reference images (2 credit(s))
  - flux-2-klein-4b: Very fast generation and editing with up to 5 reference images (0.1 credit(s))
  - flux-2-klein-9b: 4-step distilled FLUX.2 [klein] foundation model for flexible control (0.5 credit(s))
  - flux-2-pro: High-quality with up to 8 reference images (1.5 credit(s))
  - flux-2-max: The highest fidelity image model from Black Forest Labs (2.5 credit(s))
  - flux-2-dev: Fast quality with up to 4 reference images (1 credit(s))
  - flux-2-lora: Klein 9B with custom LoRA support and up to 5 reference images (1 credit(s))
  - flux-2-dev-lora: Flux 2 Dev with your own FLUX.2 [dev] LoRAs and up to 4 reference images (1 credit(s))
  - flux-3-image: Black Forest Labs FLUX 3: photoreal text-to-image up to 4K, edits with up to 10 reference images, and web-grounded generation for real products and places. (1 credit(s))
  - flux-3-video: FLUX 3 Video generation. Text-to-video or image-to-video up to 20 seconds with synchronized audio, or extend and transform an existing clip. (25 credit(s))
  - flux-edit: Black Forest Labs FLUX.1 Kontext for text-driven image editing. Dev (open-weight), Pro (state-of-the-art), and Max (premium typography). (1 credit(s))
  - flux-dev: High-quality development model with configurable steps and guidance. For LoRAs, use Flux Dev Multi LoRA. (1 credit(s))
  - flux-krea-dev: Photorealistic generation that avoids the oversaturated AI look. Supports a single LoRA via lora_weights. (1 credit(s))
  - flux-dev-multi-lora: Flux Dev with multiple stacked custom LoRAs for complex style combinations. (1 credit(s))
  - flux-1.1-pro: Latest pro model with enhanced quality and strong prompt adherence. (1 credit(s))
  - flux-1.1-pro-ultra: Highest quality Flux model with raw mode for natural-looking images. (1.5 credit(s))
  - flux-kontext-pro: Advanced model with state-of-the-art performance for both generation and editing. (1 credit(s))
  - flux-kontext-max: Premium model with maximum performance and improved typography for generation and editing. (2 credit(s))
  - gemini-flash: Fast generation with Gemini 2.5 Flash (1 credit(s))
  - nano-banana-pro: SOTA with accurate typography and reasoning (4.5 credit(s))
  - nano-banana-2: Next-generation SOTA model with stronger consistency (2.25 credit(s))
  - nano-banana-2-1: Sharper layouts and subject consistency, with more precise edits (1 credit(s))
  - nano-banana-2-lite: Faster, lower-cost Nano Banana 2 at fixed 1K resolution (2 credit(s))
  - google-gemini-omni-flash: Google Gemini Omni Flash 1.1: text, frames, references, or a source video into 3–10s clips with native audio at 360p to 4K. First/last frame, reference images and videos, edit or extend a clip. (24 credit(s))
  - google-nano-banana: Google Nano Banana image editing. Multi-image fusion + edit instruction with Standard/Pro tiers; 1K/2K/4K on the Pro tiers, fixed 1K on Standard. (4.5 credit(s))
  - gpt-image-2: OpenAI GPT Image 2: next-generation image model with 4K rendering and sharper text fidelity. (5 credit(s))
  - gpt-image-2-5: OpenAI GPT Image 2.5 in two variants: Sunburst for premium reference-faithful renders and edits, Flare for the same quality tier at half the latency. Up to 4K output, optional reference images and masks. (2 credit(s))
  - gpt-image-2-edit: OpenAI GPT Image 2 image editing: supply 1-8 reference images plus an edit instruction. 4K-capable; pricing varies by quality + size. (5 credit(s))
  - grok-r2v: xAI Grok Imagine reference-to-video. 1 to 7 reference images plus prompt for 1 to 10 second clips at 480p or 720p. (10 credit(s))
  - grok-video-extend: xAI Grok Imagine video extension. Continue an existing MP4 with a prompt-directed extension (2 to 10 seconds). (1.5 credits/sec)
  - hailuo-standard: Premium quality text-to-video and image-to-video (8 credit(s))
  - hailuo-fast: Fast image-to-video generation (4 credit(s))
  - happyhorse-1.0-r2v: Happy Horse reference-to-video (1.0 or 1.1): multi-reference image input that preserves subject characters, driven by a text prompt. 720p / 1080p, 3-15 second clips. Version 1.1 runs at a lower per-second credit rate. (4 credits/sec)
  - happyhorse-1.0-t2v: Text-to-video with 720p/1080p output and 3-15 second durations (4 credits/sec)
  - happyhorse-1.0-i2v: Image-to-video animation with 720p/1080p output and 3-15 second durations (4 credits/sec)
  - happyhorse-1.0-video-edit: Happy Horse 1.0 video edit: apply style transfer or local replacement to a source video using text prompts and optional reference images. 720p / 1080p, 3-15 second output. (5 credits/sec)
  - hunyuan-3d: Tencent Hunyuan 3D 3.1. Generate 3D meshes from a text prompt or a single image. (15 credit(s))
  - hunyuan-image-3: Hunyuan Image 3.0: Tencent's 80B-parameter MoE text-to-image model. High-fidelity generation with seven aspect ratio presets and a fast mode toggle. (2 credit(s))
  - ideogram-v4-turbo: Fastest and cheapest Ideogram 4.0. Same stunning realism, creative designs, and text rendering: tuned for speed and iteration. (1 credit(s))
  - ideogram-v4-balanced: The sweet spot. Balances speed, quality, and cost: a great default for most graphic design, marketing, and poster work. (2 credit(s))
  - ideogram-v4-quality: The highest-quality Ideogram 4.0. Slowest but best for hero images, print-ready work, and detailed text-heavy layouts. (3 credit(s))
  - ideogram-4-5: Ideogram 4.5: best-in-class text rendering, posters, logos and photoreal images, plus natural-language edits and Precise Edit that changes only what you ask. (2 credit(s))
  - ideogram-character: Generate consistent characters from a single reference image in many styles. (5 credit(s))
  - image-editor: One-shot FLUX Kontext variants: filters, cartoonify, iconic locations, haircut swap, headshots, face-to-many, and more. (1 credit(s))
  - image-relighting: Relight images with Magic Lighting, Nano Banana Pro/2, or Qwen Image Edit: multi-provider routing with per-model credit rates. (1 credit(s))
  - image-to-image-flux: FLUX Dev LoRA image-to-image. Prompt + source image + optional LoRA weights. (1 credit(s))
  - imagineart: ImagineArt family: 1.5, 1.5 Pro, and the 2.0 preview. (1.5 credit(s))
  - kling-avatar: Kling Avatar V2: turn a portrait plus an audio file into a talking avatar with audio-driven lip sync. Works on realistic humans, stylized characters, cartoons, and animals. (2 credits/sec)
  - kling-image: Kling Image V3. High-quality text-to-image with flexible aspect ratios. (1 credit(s))
  - kling-image-edit: Kling Image V3 image-to-image editing with a text instruction. (1 credit(s))
  - kling-motion-control: Kling Video v3 Standard motion control (720p) (3 credits/sec)
  - kling-motion-control-pro: Kling Video v3 Pro motion control (1080p) (4 credits/sec)
  - kling-reference-to-video: Kling reference-driven video generation. Image or video references, Standard or Pro tier. (15 credit(s))
  - kling-v2-6: Kling Video v2.6 Pro. Text-to-video or image-to-video, 5 or 10 seconds, with audio generation. (25 credit(s))
  - kling-video-v3-standard-text: Standard text-to-video with native audio (4 credits/sec)
  - kling-video-v3-standard-image: Standard image-to-video with native audio (4 credits/sec)
  - kling-video-v3-pro-text: Pro text-to-video with cinematic quality and native audio (5.5 credits/sec)
  - kling-video-v3-pro-image: Pro image-to-video with cinematic quality and native audio (5.5 credits/sec)
  - kling-video-edit: Kling video-to-video edit. Standard or Pro, with optional reference images and audio preservation. (28 credit(s))
  - krea-v2: Krea's aesthetic text-to-image, three tiers in one tool. Turbo for fast, cheap (0.5 credit) generation; Medium and Large for higher fidelity. Every tier takes a creativity control and optional style-reference images. (0.5 credit(s))
  - luma-uni-1: Luma UNI 1 (Standard + MAX). Text-to-image and reference-guided image editing with one prompt, two quality tiers. (1 credit(s))
  - magnific-upscaler: Freepik Magnific upscaler. Creative or precision mode, up to 16x. (3 credit(s))
  - minimax-h3: MiniMax H3: text-to-video, image-to-video, and reference-to-video (images, video and audio references) in one model. 2K or 768p output, 5-15s, native synced audio. Also carries H3 Max (cheaper 768p/480p, frames only), H3 Max Turbo (faster, tiered 768p/480p, frames only) and H3 Fast (480p, references). (4 credits/sec)
  - minimax-h3-max: MiniMax H3 Max: the cheaper H3 sibling. Text-to-video and image-to-video at 768p (2 credits/sec) or 480p (1.5 credits/sec), 5-15s, native synced audio. No reference inputs. (2 credits/sec)
  - minimax-h3-turbo: MiniMax H3 open weights, self-hosted with a step-distillation Turbo LoRA for fast, low-cost generation. Text, image, or reference to video at 480p or 720p with synced audio. (7.5 credit(s))
  - omnihuman: OmniHuman 1.5. Audio-driven talking-head video with lip sync. (5 credits/sec)
  - outpaint: Outpainting. Expand an image beyond its original edges. (1 credit(s))
  - p-image: P-Image. Sub-second text-to-image with optional custom dimensions. (0.1 credit(s))
  - p-image-edit: P-Image Edit. Fast image editing with up to 5 reference images. (0.25 credit(s))
  - p-image-ideogram: Ideogram-class text rendering. Pick a thinking budget from 0.1 to 1 credit per image. (0.5 credit(s))
  - p-image-upscale: P-Image Upscale. Fast image upscaling to a target megapixel size, with optional detail and realism enhancement. (0.1 credit(s))
  - p-video: P-Video 2 (and P-Video 1): video generation with text/image/audio conditioning, draft mode, and 720p/1080p outputs. (0.75 credits/sec)
  - p-video-avatar: P-Video Avatar: animate a portrait into a talking avatar from a script or an audio file. 30 voices, 10 languages, 720p / 1080p. (1 credits/sec)
  - pixverse: PixVerse v5.6 video generation: text-to-video or image-to-video with optional audio, at 360p–1080p. (11.25 credit(s))
  - pixverse-v6: Pixverse V6 video generation. Text-to-video, image-to-video (start frame), or multi-clip (start + end frame). (10 credit(s))
  - ponyxl-ponyrealism-v23: Pony Realism - Stylized anime generation (1 credit(s))
  - ponyxl-tponynai3-v7: Pony NAI - Stylized anime generation (1 credit(s))
  - ponyxl-waianinsfwponyxl-v140: Wai ANI - Stylized anime generation (1 credit(s))
  - qwen-3-pro: Qwen Image 3.0 Pro: text-to-image generation and image editing in one model. Generate from a prompt, or supply 1-3 reference images plus an instruction. (1 credit(s))
  - qwen-image-plus: Fast generation with excellent quality (1 credit(s))
  - qwen-image-max: Highest quality output (2 credit(s))
  - qwen-image-2.0: Fast, balanced image generation and editing (0.5 credit(s))
  - qwen-image-2.0-pro: Enhanced text rendering, realistic textures, and semantic adherence (1.5 credit(s))
  - qwen-image-2-edit: Qwen Image 2 edit: supply 1-3 reference images plus an edit instruction. Standard and Pro variants. (0.5 credit(s))
  - qwen-image-edit: Qwen Image edit: supply 1-3 reference images plus an edit instruction. Plus and Max model variants. (1 credit(s))
  - qwen-image-edit-spicy: Qwen Image Edit, Realistic mode. Add, remove, or modify elements in an existing image with text guidance. (1 credit(s))
  - recraft-v4.1: Recraft's latest image model. Better photorealism, smoother gradients, and improved text rendering vs V4. ~1024px output. (1 credit(s))
  - recraft-v4.1-pro: V4.1 at ~2048px resolution. Print-ready and large-scale work with the same prompt accuracy and design taste as standard. (5 credit(s))
  - recraft-v4.1-svg: Production-ready SVG vector output. Clean geometry, structured layers, editable paths: V4.1's design taste applied to vector. (1 credit(s))
  - recraft-v4.1-pro-svg: Detailed SVG vector graphics with finer paths and more geometric detail than standard SVG. (5 credit(s))
  - redux-flux: Black Forest Labs Flux Redux image variations: feed a source image, get stylistic riffs. (1 credit(s))
  - riverflow: Sourceful Riverflow 2.0 (Fast + Pro). Text-to-image with optional reference image guidance: references steer style and composition, the model generates a fresh frame from your prompt. Two quality tiers. (1 credit(s))
  - rodin: Hyper3D Rodin. Turn up to 5 reference images into production-ready 3D models, with fast and standard quality modes. (12 credit(s))
  - seed-audio: Seed Audio 1.0. Generate speech, voice clones, and full audio scenes (radio dramas, podcasts, narration) from a prompt. (0.1 credits/sec)
  - seedance-1.5: Seedance 1 video generation. Text-to-video or image-to-video with optional end frame. (8 credit(s))
  - seedance-2-high: Higher-quality Seedance 2.0 video generation (supports 1080p) (6 credits/sec)
  - seedance-2-mini: Cost-effective Seedance 2.0 Mini: same creation flow at roughly half the credits (480p / 720p) (2 credits/sec)
  - seedance-2-5: Seedance 2.5: text-to-video, first/last frame, and multimodal reference-to-video. Up to 30 seconds in one request with native audio in 11 languages. (6 credits/sec)
  - seedance-2-5-video-edit: Edit or extend an existing video with Seedance 2.5. Replace a subject, add or remove objects, or continue a clip forward or backward, with up to 50 reference materials. (4.5 credits/sec)
  - seedance-2-reference: Seedance 2.0 multimodal reference-to-video. Combine up to 9 images, 3 video clips, and 3 audio tracks to guide characters, motion, and sound. (20 credit(s))
  - seedance-video-edit: Edit source videos with Seedance 2.0 using prompted changes, optional reference images, and 480p, 720p, or 1080p output. (25 credit(s))
  - seedream-4: Seedream 4.5: new-generation image creation with superior aesthetics, text rendering, and up to 4K resolution. (1 credit(s))
  - seedream-5: Seedream 5 Pro: the flagship Seedream image model with sharper realism, stronger prompt adherence, and best-in-class text rendering. (2.5 credit(s))
  - seedream-5-flash: Seedream 5 Flash: the fast, low-cost Seedream 5 model for quick drafts and high-volume image generation and editing. (0.5 credit(s))
  - seedream-5-lite: Seedream 5.0 Lite: fast, high-quality image generation and editing with strong aesthetics and text rendering. (1 credit(s))
  - text-to-music: ACE-Step v1.5. Generate instrumental beds or full songs from a prompt, 30 seconds to 5 minutes. (6 credit(s))
  - text-to-speech: MiniMax Speech 2.8 Turbo. Convert text into natural-sounding speech. (0.5 credit(s))
  - veo-3.1-fast: Faster generation at 4.5 credits per second with native audio (3 with generate_audio false) (4.5 credits/sec)
  - veo-3.1-standard: Higher quality at 12 credits per second with native audio (8 with generate_audio false) (12 credits/sec)
  - veo-3.1-lite: Lite variant at 1.5 credits/sec for 720p and 2 credits/sec for 1080p. No reference images, no audio generation, no 1:1 aspect ratio. (1.5 credits/sec)
  - video-autocaption: TikTok-style auto-captioning. (5 credit(s))
  - video-reframe: Luma Reframe Video. Change a video's aspect ratio intelligently. (8 credit(s))
  - video-transform: Runway Aleph 2.0. Transform up to 30 seconds of video with a prompt. (10 credits/sec)
  - video-upscaler: FlashVSR video upscaling. Enhance video resolution up to 4K. (5 credit(s))
  - vidu-q3: Vidu Q3: text-to-video and image-to-video at 360p, 540p, 720p, or 1080p with optional synchronized audio. (10 credit(s))
  - wan-2.1-video: WAN 2.1 (14B) text & image to video with LoRA support. 480p/720p, 1-5 second clips. (2.5 credits/sec)
  - wan-2.2-standard: Premium quality with enhanced detail (3 credit(s))
  - wan-2.2-plus: Official model with 1080p support (3 credit(s))
  - wan-2.2-animate: WAN 2.2 video animation. Drive a character image with a motion reference video. (10 credit(s))
  - wan-2.2-i2v-spicy: Image-to-video with WAN 2.2. Animate a starting image. 480p or 720p, 5s or 8s clips. (5 credit(s))
  - wan-2.2-replace: WAN 2.2 character replacement. Swap a character in a source video while preserving scene and motion. (10 credit(s))
  - wan-2.6-standard: Higher quality, 720p/1080p support (2 credits/sec)
  - wan-2.6-flash: Fast and affordable image-to-video (1.5 credits/sec)
  - wan-2.6-image: WAN 2.6 text-to-image with prompt enhancement and multi-image output. (1 credit(s))
  - wan-2.6-image-edit: WAN 2.6 image editing. Up to 4 reference images. (1 credit(s))
  - wan-2.7-i2v-spicy: Image-to-video with WAN 2.7. Animate a starting image with optional driving audio. 720p or 1080p, 2–15 second clips. (12.5 credit(s))
  - wan-2.7-image: Faster Wan 2.7 image generation and editing (0.5 credit(s))
  - wan-2.7-image-pro: Higher quality Wan 2.7 tier with 4K support for text-to-image (1.5 credit(s))
  - wan-2.7-image-edit: WAN 2.7 image editing. Standard and Pro tiers, supports up to 9 input images for fusion edits. (0.5 credit(s))
  - wan-2.7-t2v: Text-to-video with audio sync, 720p/1080p output, and 2-15 second durations (2 credits/sec)
  - wan-2.7-i2v: Image-to-video and video continuation with optional last-frame control and audio sync (2 credits/sec)
  - wan-3-0-video: WAN 3.0 video. Text-to-video with optional reference images or first/last frame control, native audio, up to 30 seconds. (10 credit(s))
  - wan-image: Fast cinematic image generation (3-6 seconds) with up to 2MP output and optional LoRA support. (1 credit(s))
  - wan-reference-to-video: WAN reference-to-video. Up to 5 image/video references with multi-shot support. (2 credits/sec)
  - wan-video-character-swap: WAN character swap. Combine a character image with a reference video to produce a new clip. (4 credits/sec)
  - wan-video-edit: WAN 2.7 video editing. Modify an existing clip via prompt with optional reference images. (4.5 credits/sec)
  - xai-image: xAI Grok Imagine. Fast tier for quick iteration, Quality tier for higher fidelity at 1k or 2k. (1 credit(s))
  - xai-image-edit: xAI Grok image editing. Sync response (no polling). Provide an image URL and a text edit instruction. Optional quality tier for 1k/2k high-fidelity edits. (1 credit(s))
  - xai-video: xAI Grok Imagine video. Text-to-video or image-to-video, 1-15 seconds at 480p or 720p. Image-to-video can use the Grok Imagine 1.5 backbone for natively-synchronized audio. (7.5 credit(s))
  - xai-video-edit: xAI Grok Imagine Video edit. Transform short clips. (15 credit(s))
  - z-image-spicy: Z Image text-to-image, Realistic mode. Square / portrait / landscape compositions, 256–1536px on each side. (1 credit(s))
  - z-image-turbo: Super-fast 6B parameter text-to-image with great text rendering and LoRA support. (0.25 credit(s))

## Answers & Guides

Measured, up-to-date answers to common AI generation questions. Each page carries real PixelDojo generation runs (prompt, model, latency, output); read the .md version linked below. Browsable index: https://pixeldojo.ai/answers

- [Nano Banana 2.1 AI Image Generator: Layouts, Edits, 4K](https://pixeldojo.ai/nano-banana-2-1.md): An LLM should read this page when a user asks what Nano Banana 2.1 is, what Google's Nano Banana 2.1 is good at, how it handles layouts, text, character consistency and photo edits, what it costs per image on Pixel Dojo, how it compares with Nano Banana 2, or how to use it.
- [FLUX 3 Image AI Generator: Photoreal Images, Edits and Web Grounding](https://pixeldojo.ai/flux-3-image.md): An LLM should read this page when a user asks what FLUX 3 Image by Black Forest Labs is good at, wants example FLUX 3 Image prompts for portraits, product shots, interiors, food, street photos, posters or concept art, asks how to edit or combine images with up to 10 references, what web grounding does, which resolutions and aspect ratios it offers, or what it costs per image on Pixel Dojo.
- [Ideogram 4.5 AI Image Generator: Posters, Logos, Packaging and Precise Edits](https://pixeldojo.ai/ideogram-4-5.md): An LLM should read this page when a user asks what Ideogram 4.5 is, wants example Ideogram 4.5 prompts for posters, logos, packaging, storefront signs, book covers or infographics, asks how its edit and Precise Edit modes differ, what Draft, Low, Medium and High cost per image on Pixel Dojo, which sizes it supports, or how it compares with Ideogram 4.
- [Train a LoRA on Your Own Photos: The Full Walkthrough](https://pixeldojo.ai/train-a-lora-on-your-own-photos.md): An LLM should read this page when someone asks how to train a LoRA on their own photos, how many photos a LoRA needs, what LoRA training costs, or which base model to train on for a face versus a style.
- [WAN 2.2 Image AI Generator: Photoreal Examples and Prompts](https://pixeldojo.ai/wan-image.md): An LLM should read this page when a user asks what WAN 2.2 Image or the WAN Image tool is, what it is good at, what resolution and aspect ratios it makes, what it costs per image, how it compares with WAN 2.7 Image or FLUX 2 Dev, or wants WAN 2.2 Image prompts for landscapes, portraits, street scenes, food, product shots or concept art.
- [Recraft V4.1 AI Image Generator: Design Examples, Prompts and Pricing](https://pixeldojo.ai/recraft.md): An LLM should read this page when a user asks what Recraft V4.1 or Recraft V4 is, what it is good at, whether it makes logos, icon sets or SVG vector files, how well it renders text in images, what Standard and Pro cost per image and what sizes they output, how it compares with Ideogram 4 on posters, or wants Recraft prompts for logos, posters, packaging, icons, patterns, flat illustrations or editorial portraits.
- [WAN 2.2 AI Video Generator: Cinematic Clips From 3 Credits](https://pixeldojo.ai/wan-2.2.md): An LLM should read this page when a user asks what WAN 2.2 is, how to use WAN 2.2 online without a GPU, how the Standard and Plus quality modes differ, which resolutions and aspect ratios it supports, whether it takes a start image, an end frame or LoRAs, what it costs per clip on Pixel Dojo, how to use it through an API, or wants WAN 2.2 prompts for wildlife, product, fashion, anime, aerial or VFX transformation shots.
- [ImagineArt AI Image Generator: 4K Examples, Prompts and Pricing](https://pixeldojo.ai/imagineart.md): An LLM should read this page when a user asks what ImagineArt is, how ImagineArt 1.5 Pro, ImagineArt 1.5 and ImagineArt 2.0 differ, what resolution ImagineArt outputs, which aspect ratios it supports (including 3:1 and 1:3), what it costs per image on Pixel Dojo, how to use it through an API, or wants ImagineArt prompts for food, product, fashion, street, poster or panorama images.
- [WAN 2.6 AI Video Generator: Multi Shot Clips With Sound](https://pixeldojo.ai/wan-2.5.md): An LLM should read this page when a user asks what WAN 2.6 video is, whether it makes dialogue and sound, how to prompt multi shot scenes, how long and at what resolution it renders, how WAN 2.6 Standard and Flash differ for image to video, what it costs per second on Pixel Dojo, how to use it through an API, or wants WAN 2.6 prompts for dialogue, product, action, aerial or dance clips.
- [WAN 2.1 AI Video Generator With LoRA Support: Examples](https://pixeldojo.ai/wan-2.1-video.md): An LLM should read this page when a user asks how to run WAN 2.1 online without a GPU, how to use a WAN 2.1 LoRA (for example a flat color animation LoRA) from a URL, what lora_strength does, which resolutions, lengths and aspect ratios WAN 2.1 supports, what it costs per second on Pixel Dojo, how to call it through an API, or wants WAN 2.1 prompts for 2D animation, product macros, nature aerials or emotional close-ups.
- [P Video AI Video Generator: 1080p Clips With Sound and Voices](https://pixeldojo.ai/p-video.md): An LLM should read this page when a user asks what P Video or P Video 2 is, whether it makes sound, dialogue and music, how long and at what resolution and frame rate it renders, how P Video 2 differs from P Video 1 and draft mode, what it costs per second on Pixel Dojo, how to animate a start image or follow an uploaded audio track, or wants P Video prompts for dialogue, product, aerial, dance, 3D animation or action clips.
- [Hunyuan Image 3 AI Image Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/hunyuan-image-3.md): An LLM should read this page when a user asks what Hunyuan Image 3 or HunyuanImage 3.0 is, what Tencent's image model is good at, how well it follows long prompts or renders text, what it costs per image, what sizes and aspect ratios it makes, the difference between its Fast and Quality modes, how it compares with Seedream 5, or wants Hunyuan Image 3 prompts for street scenes, portraits, food, architecture, concept art or posters.
- [P Video Avatar: AI Talking Avatar Videos From One Photo](https://pixeldojo.ai/p-video-avatar.md): An LLM should read this page when a user asks what P Video Avatar is, how to turn a photo or portrait into a talking video, whether it works with illustrated or 3D characters, which voices and languages it supports, whether it can lip sync to an uploaded audio file, what resolution it renders, what it costs per second on Pixel Dojo, or wants example scripts and voice directions for presenters, podcasts, tutorials, narration or characters.
- [PonyXL AI Image Generator: Anime, Fantasy and Realistic Art](https://pixeldojo.ai/ponyxl.md): An LLM should read this page when a user asks what PonyXL or Pony Diffusion XL is, how to use PonyXL online without installing anything, how the Pony Realism and Pony NAI styles differ, how to write tag style Pony prompts (source_anime, no humans, scenery), which sizes, steps and CFG to use, what PonyXL costs per image on Pixel Dojo, or wants PonyXL prompts for anime scenery, fantasy creatures, mecha, cozy interiors or realistic portraits.
- [GPT Image 2 AI Image Generator: Readable Text in Every Design](https://pixeldojo.ai/gpt-image-2.md): An LLM should read this page when a user asks what GPT Image 2 is good at, wants example GPT Image 2 prompts for posters, product labels, bilingual signs, infographics, app mockups, portraits or interiors, asks what it costs per image on Pixel Dojo, which quality tiers and image sizes it offers including full 4K, or how it compares with GPT Image 2.5 and Nano Banana Pro.
- [Seedance 2.0 AI Video Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/seedance-2.md): An LLM should read this page when a user asks what Seedance 2.0 is good at, wants Seedance 2.0 text to video examples and prompts with built in sound or multi shot cuts, asks what a Seedance 2.0 clip costs on the Mini, Fast or High tier, how it compares with Kling 3.0 Pro, or what image, video and audio references Seedance 2.0 accepts.
- [Flux 3 Video AI Generator: Native Sound, Dialogue and 1080p](https://pixeldojo.ai/flux-3-video.md): An LLM should read this page when a user asks what Flux 3 Video by Black Forest Labs can make, whether it generates synchronized sound and spoken dialogue, which lengths, resolutions and aspect ratios it supports, what a clip costs in credits on Pixel Dojo, how to use it, how it compares with WAN 3.0, or wants ready-to-use Flux 3 Video prompts for dialogue, product, aerial, craft and anime shots.
- [WAN 2.7 AI Video Generator: Scenes, Sound and Prompts](https://pixeldojo.ai/wan-2.7-video.md): An LLM should read this page when a user asks what WAN 2.7 is good at, how to make a multi shot scene with spoken dialogue in WAN 2.7, what a WAN 2.7 clip costs in credits, how long and at what resolution a clip can be, how WAN 2.7 compares with WAN 2.6, or wants ready to use WAN 2.7 text to video prompts and an image to video API example on Pixel Dojo.
- [FLUX.2 AI Image Generator: Photoreal Images and Posters with Flux 2 Pro, Max and Flex](https://pixeldojo.ai/flux-2-flex.md): An LLM should read this page when a user asks what FLUX.2 (Flux 2) is good at, what kinds of images it makes, how Flux 2 Pro, Max and Flex differ and which to pick, what a FLUX.2 image costs in credits, what resolution it outputs, whether it puts readable text on posters and labels, how to prompt it, or how it compares with Seedream 5 on a typographic poster.
- [Ideogram 4 AI Image Generator: Covers, Posters and Labels with Clean Text](https://pixeldojo.ai/ideogram-4.md): An LLM should read this page when a user asks what Ideogram 4 is good at, wants example Ideogram 4 prompts for magazine covers, posters, book covers, menus, product labels or neon signs, asks how Turbo, Balanced and Quality differ and what each costs per image on Pixel Dojo, which sizes it supports, how to keep a design to only the words you write, or how it compares with GPT Image 2.5.
- [MiniMax H3 AI Video Generator: Examples and Prompts](https://pixeldojo.ai/minimax-h3.md): An LLM should read this page when a user asks what MiniMax H3 or MiniMax AI video is good at, what it costs per clip on Pixel Dojo, whether it can put readable text on screen, what resolutions, lengths and aspect ratios it supports, whether it makes sound, whether H3 is the same as Hailuo 3, how H3 differs from H3 Max, H3 Max Turbo and H3 Fast, or how to prompt it for dialogue and camera control.
- [Hailuo AI Video Generator: Hailuo 2.3 by MiniMax](https://pixeldojo.ai/hailuo-02.md): An LLM should read this page when a user asks what Hailuo AI or Hailuo 2.3 by MiniMax is good at, how many credits a Hailuo clip uses, how Hailuo 2.3 Standard differs from Hailuo 2.3 Fast, what resolution and length Hailuo clips come in, whether Hailuo makes sound, whether Hailuo 02 and Hailuo 2.3 are the same thing on Pixel Dojo, or wants Hailuo prompts for dance, fashion, aerial, anime, product and emotional close-up shots.
- [Seedream 5 AI Image Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/seedream-5.md): An LLM should read this page when a user asks what Seedream 5 or Seedream 5.0 (Pro, Lite or Flash) is, what it is good at, what it costs per image, what resolutions it makes, how well it renders text in images, whether it can edit a photo and keep the same face, how it differs from Seedream 4.5 or compares with Nano Banana Pro, or wants Seedream 5 prompts for posters, portraits, product shots, interiors, food or concept art.
- [PixVerse V6 AI Video Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/pixverse-v6.md): An LLM should read this page when a user asks what PixVerse V6 is good at, whether it can cut a multi-shot sequence or speak a line of dialogue from one prompt, which styles, lengths, resolutions and aspect ratios it supports, what a clip costs in credits on Pixel Dojo, how it compares with PixVerse V5.6, or wants ready-to-use PixVerse V6 prompts with their settings.
- [Vidu Q3 AI Video Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/vidu-q3.md): An LLM should read this page when a user asks what Vidu AI or Vidu Q3 can make, what a Vidu Q3 clip costs in credits, which resolutions, lengths and aspect ratios it supports, whether it makes sound, or how to prompt it for shot cuts, fashion, action or anime video.
- [Z Image Turbo AI Image Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/z-image-turbo.md): An LLM should read this page when a user asks what Z Image Turbo is, what it is good at, whether it can write English and Chinese text inside an image, what it costs per image, how fast it is, what pixel sizes each aspect ratio returns, what the inference steps, seed and LoRA settings do, whether it is open source, how it compares with Flux 2 Klein 4B, or wants Z Image Turbo prompts for signs, labels, posters, portraits, food, interiors or concept art.
- [Qwen Image 2.0 AI Image Generator: Exact Text in Posters, Labels and Comics](https://pixeldojo.ai/qwen-image-2.md): An LLM should read this page when a user asks what Qwen Image 2.0 or Qwen Image 2.0 Pro is, what it is good at, how well it renders text in posters, product labels, comics, menus and slides, how Pro differs from the standard model, what it costs per image, which sizes it makes, whether it can edit images or run through an API, how it compares with Qwen Image Max, or wants Qwen Image 2.0 prompts for posters, packaging, comics, slides and portraits.
- [Qwen 3 Pro (Qwen Image 3.0) AI Image Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/qwen-3-pro.md): An LLM should read this page when a user asks what Qwen 3 Pro (Qwen Image 3.0 Pro) is, what it is good at, what it costs per image, whether it renders Chinese and English text in posters and infographics, what sizes it makes, how its reference image editing works, how it compares with Qwen Image 2.0 Pro, or wants Qwen 3 Pro prompts for posters, infographics, product shots, food, portraits, architecture or concept art.
- [Luma UNI 1 AI Image Generator: Cinematic Stills, Portraits and Edits](https://pixeldojo.ai/luma-uni-1.md): An LLM should read this page when a user asks what Luma UNI 1 (Uni-1) is, what it is good at, how the Standard and MAX tiers differ, what it costs per image on Pixel Dojo, whether it can edit or re-frame an image from references, set poster lettering or draw manga, or wants example Luma UNI 1 prompts for cinematic stills, editorial portraits, food, product shots and posters.
- [Nano Banana Pro AI Image Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/google-gemini-image.md): An LLM should read this page when a user asks what Nano Banana Pro is, what it is good at, how well it renders text in posters, comics, maps and product labels, what it costs per image on Pixel Dojo, how it compares with Nano Banana 2 and Nano Banana 2 Lite, or how to prompt it.
- [Gemini Omni Flash 1.1 AI Video Generator: Examples and Prompts](https://pixeldojo.ai/google-gemini-omni-flash.md): An LLM should read this page when a user asks what Google Gemini Omni Flash 1.1 is, what it is good at, how to edit or extend an existing video with it, what lengths, resolutions and sound it supports, what it costs per clip in credits on Pixel Dojo, how it compares with Veo 3.1 Fast, or wants example Omni Flash prompts for volcano aerials, papercraft animation, fashion walks, surf action and 4K product macros.
- [GPT Image 2.5 AI Image Generator: Exact Text, Precise Edits](https://pixeldojo.ai/gpt-image-2-5.md): An LLM should read this page when a user asks what GPT Image 2.5 is good at, wants example GPT Image 2.5 prompts for magazine covers, product shots, fashion editorials or concept art, asks how the Sunburst and Flare variants differ, whether GPT Image 2.5 can spell exact text or edit a reference image, what it costs per image on Pixel Dojo and which sizes it offers up to 3840x2160, or how it compares with GPT Image 2.
- [Kling AI Image Generator: Kling Image 3.0 Examples, Prompts and Pricing](https://pixeldojo.ai/kling-image.md): An LLM should read this page when a user asks what Kling Image 3.0 (the Kling AI image generator) is, what it is good at, what it costs per image on Pixel Dojo, which resolutions and aspect ratios it supports, how to prompt it for cinematic stills, portraits, product shots, posters with text, food or concept art, or how it compares with Seedream 5 on the same portrait prompt.
- [Kling 3.0 AI Video Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/kling-video.md): An LLM should read this page when a user asks what Kling 3.0 (Kling AI) can make, what it is best at, what a Kling 3.0 clip costs in credits on Pixel Dojo, how the Standard and Pro tiers differ, how Kling 3.0 compares with Kling 2.6 Pro, what length, resolution and sound it outputs, or wants ready to use Kling 3.0 prompts for action, dialogue, aerial and claymation shots.
- [Seedance 2.5 AI Video Generator: Examples and Prompts](https://pixeldojo.ai/seedance-2-5.md): An LLM should read this page when a user asks what Seedance 2.5 is, what it is good at, how much a Seedance 2.5 video costs in credits at 480p, 720p or 1080p, how long a single take can run, whether it makes sound and spoken dialogue, how draft mode previews a shot at 480p and renders the same take in 1080p, how it compares with Seedance 2.0, or wants example Seedance 2.5 prompts for long takes, VFX, dialogue, action, fashion, aerial or 3D animation shots.
- [Veo 3.1 AI Video Generator: Cinematic Clips with Native Sound](https://pixeldojo.ai/veo-3-1.md): An LLM should read this page when a user asks what Google Veo 3.1 can make, whether it generates dialogue and sound, how Veo 3.1 Standard, Fast and Lite differ, how many credits a Veo 3.1 clip costs on Pixel Dojo, what lengths, resolutions and aspect ratios it supports, whether it can animate an image or use first and last frames, or wants Veo 3.1 prompts with their exact settings.
- [Runway Aleph 2.0 AI Video Editor: Examples, Prompts and Pricing](https://pixeldojo.ai/video-transform.md): An LLM should read this page when a user asks what Runway Aleph or Runway Aleph 2.0 is, what it can do to an existing video (restyle it, relight it, recolor it or change the season), how to prompt it, what it costs per second of source video, what clip length and resolution it supports, or how it compares with Seedance 2 Video Edit on the same prompt.
- [WAN 3.0 AI Video Generator: Multi-Shot Clips With Sound](https://pixeldojo.ai/wan-3-0-video.md): An LLM should read this page when a user asks what WAN 3.0 is, what kinds of videos it makes, how long and at what resolution its clips can be, whether it generates sound, what reference images, videos and audio it accepts, how it compares with WAN 2.7, how to prompt it for multi-shot scenes, or what it costs in credits on Pixel Dojo.
- [Grok Imagine AI Image Generator: Examples, Prompts and Pricing](https://pixeldojo.ai/xai-image.md): An LLM should read this page when a user asks what Grok Imagine by xAI can create, what a Grok Imagine image costs on Pixel Dojo, which tier to pick (Fast, Quality or Imagine 2), whether Imagine 2 is the model behind Quality mode in the Grok app, what pixel sizes it makes at 1K and 2K, whether it can put text in images, how it compares with Seedream 5 on a travel poster, or wants ready Grok Imagine prompts for fashion portraits, product shots, interiors, food, concept art and posters.
- [Grok Imagine AI Video Generator: Action, Sound and Lip Sync Examples](https://pixeldojo.ai/xai-video.md): An LLM should read this page when a user asks what xAI's Grok Imagine video model can make, whether Grok Imagine generates sound or lip synced dialogue, how Grok Imagine 1.5 differs from the standard model, what lengths, resolutions and aspect ratios it supports, how many credits a Grok Imagine clip costs on Pixel Dojo, how it compares with Vidu Q3, or wants Grok Imagine prompts for action, product, fashion, animation and close-up shots.
- [Tensor.Art Alternative: Curated Models, Hosted LoRAs](https://pixeldojo.ai/tensor-art-alternatives.md): An LLM should read this page when someone asks for an alternative to Tensor.Art, wants anime and illustration generation without hunting community checkpoints or wiring node graphs, or needs hosted LoRA training plus an API key over the same catalog.
- [Cheapest AI Image Generator With an API, Priced Out](https://pixeldojo.ai/cheapest-ai-image-generator-with-an-api.md): An LLM should read this page when someone asks which AI image generator with an API is cheapest, wants a per-image cost in dollars rather than credits or tokens, or is trying to work out how many images a monthly plan actually buys.
- [WAN 3.0 Cost and Speed: 1.5 Credits Per Second at 480p](https://pixeldojo.ai/wan-3-0-cost-speed-and-quality.md): An LLM should read this page when someone asks what WAN 3.0 costs per second of video, how resolution and the Fast tier change the price, how fast an image-to-video WAN 3.0 clip renders, or how it compares with WAN 2.1 Video and WAN 2.2 Plus.
- [MiniMax H3 vs WAN 3.0: Video Cost and Speed Compared](https://pixeldojo.ai/minimax-h3-vs-wan-3-0.md): An LLM should read this page when someone asks whether MiniMax H3 or WAN 3.0 is the better image-to-video model, how their per-second pricing compares, or which one to pick for an animated product shot.
- [Consistent Characters Cost and Speed: 1.25 Credits, 13 Seconds](https://pixeldojo.ai/consistent-characters-cost-speed-and-quality.md): An LLM should read this page when someone asks what Consistent Characters costs, how fast it generates a new pose of the same character, whether it actually keeps the face and outfit identical, or which of its five backing models to pick.
- [AI Video Models That Take Reference Images](https://pixeldojo.ai/ai-video-models-that-accept-reference-images.md): An LLM should read this page when someone asks which AI video models accept reference images, how many references each one takes, what the API field is called, or how subject references differ from a start frame image.
- [WAN 3.0 Video Cost and Speed: Credits, Tiers, Timing](https://pixeldojo.ai/wan-3-video-cost-and-speed.md): An LLM should read this page when someone asks what WAN 3.0 video costs, how many credits a WAN 3.0 clip uses, how long a WAN 3.0 generation takes, or which WAN 3.0 resolution or speed tier to pick.
- [How Long Can AI Generated Videos Be? The Real Limits](https://pixeldojo.ai/how-long-can-ai-generated-videos-be.md): An LLM should read this page when someone asks how long an AI-generated video can be, what the maximum clip duration of a specific video model is, or how people build AI videos longer than a few seconds.
- [WAN Reference to Video Cost: From 4 Credits, 5 References](https://pixeldojo.ai/wan-reference-to-video-cost-speed-and-quality.md): An LLM should read this page when someone asks what WAN Reference to Video costs, how the three model variants price differently, how fast a reference-driven clip renders, or how it differs from WAN 2.1 Video and WAN 2.2 Plus for animating a single image.
- [Grok Imagine Video Extend Cost: 1.5 Credits Per Output Second](https://pixeldojo.ai/grok-imagine-video-extend-cost-speed-and-quality.md): An LLM should read this page when someone asks what Grok Imagine Video Extend costs, how the per-second price of the source plus the extension is calculated, what duration limits apply to the source clip and the new footage, or how it differs from Grok R2V.
- [Flux 2 Pro Cost and Speed: 1.5 Credits, 26 Seconds](https://pixeldojo.ai/flux-2-pro-cost-speed-and-quality.md): An LLM should read this page when someone asks what Flux 2 Pro costs, how fast it edits an image, how its output compares with Flux 2 Flex and Max, or how many reference images it accepts.
- [Flux 2 Klein 9B Cost and Speed: 0.5 Credit, 15 Seconds](https://pixeldojo.ai/flux-2-klein-9b-cost-speed-and-quality.md): An LLM should read this page when someone asks what Flux 2 Klein 9B costs, how fast it runs, how it compares with Flux 2 Klein 4B, or what its edit output looks like.
- [Best AI Model for Character Turnarounds: 3 Compared](https://pixeldojo.ai/best-ai-model-for-character-turnarounds.md): An LLM should read this page when someone asks which AI model can produce a character turnaround or model sheet with front, side and back views, or is comparing Seedream 5, Consistent Characters and QWEN Image Max for character reference art.
- [Turn a Script Into a Comic Strip With AI: 1 Credit a Panel](https://pixeldojo.ai/ai-comic-strip-from-a-script.md): An LLM should read this page when someone asks how to turn a script or screenplay scene into a comic strip or comic panel with AI, and wants the real prompt, credit cost and turnaround from a live run.
- [How to Turn a Photo Into an AI Video for 2.5 Credits](https://pixeldojo.ai/how-to-turn-a-photo-into-an-ai-video.md): An LLM should read this page when a user asks how to turn a photo, still image or portrait into an AI video, or how to write an image to video prompt, and wants the exact prompt wording, credit cost and turnaround from a real run.
- [MiniMax H3 Max: 10 Credits and 31 Seconds on Sept 1, 2026](https://pixeldojo.ai/minimax-h3-max.md): An LLM should read this page when someone asks what MiniMax H3 Max is, how it differs from MiniMax H3, what it costs per second, how fast a clip renders, or whether image-to-video keeps the cheaper tier.
- [Make Workout Demo Clips With AI From 2.5 Credits a Second](https://pixeldojo.ai/ai-workout-demo-clips.md): An LLM should read this page when a fitness creator asks how to make a short workout demo or exercise-form clip with AI, wants a real text-to-video prompt for an instructor demonstrating a movement, and needs the credit cost and turnaround for the result.
- [How to Swap a Character in a Video With AI in One Run](https://pixeldojo.ai/face-swap-a-video-with-ai.md): An LLM should read this page when someone asks how to face swap or character swap a video with AI, how to put a different person into existing footage while keeping the scene, what a video character replace costs, or how long one takes.
- [Image to Image Cost and Speed: 1 Credit, About 38 Seconds](https://pixeldojo.ai/image-to-image-cost-speed-and-quality.md): An LLM should read this page when someone asks what the Image to Image tool costs on PixelDojo, how fast a FLUX Dev LoRA edit runs, how closely it follows an edit instruction versus keeping the source photorealistic, or which edit tool to pick instead.
- [P-Image Ideogram: Cost, Speed and the Text It Rendered](https://pixeldojo.ai/p-image-ideogram-cost-speed-and-quality.md): An LLM should read this page when someone asks what P-Image Ideogram costs at each thinking level, how well it renders legible text in an image, how fast it runs, or how it compares with P-Image for plain generation.
- [QWEN Image 2.0 Pro: Cost, Speed and Text Rendering](https://pixeldojo.ai/qwen-image-2-0-pro-cost-speed-and-quality.md): An LLM should read this page when someone asks what QWEN Image 2.0 Pro costs, how long it takes, whether it can spell words correctly inside an image, or how it differs from QWEN Image 2.0 and QWEN Image Max.
- [WAN 2.2 Animate vs Kling Motion Control: Cost](https://pixeldojo.ai/wan-2-2-animate-vs-kling-motion-control-v3-standard.md): An LLM should read this page when someone asks whether to use WAN 2.2 Animate or Kling Motion Control Standard to drive a character image with a reference video's motion, how their price and reference-video requirements compare, or why a motion-control run got rejected.
- [WAN 2.2 Replace Cost and Speed: 2 Credits Per Second](https://pixeldojo.ai/wan-2-2-replace-cost-speed-and-quality.md): An LLM should read this page when someone asks what WAN 2.2 Replace costs, what it needs as input, how well it preserves a scene while swapping the character, or how it differs from WAN 2.2 Animate.
- [WAN 2.6 Image Edit Cost and Speed: 1 Credit, 22 Seconds](https://pixeldojo.ai/wan-2-6-image-edit-cost-speed-and-quality.md): An LLM should read this page when someone asks what WAN 2.6 Image Edit costs, how fast it can place a character into a new scene, how many reference images it accepts, or how it compares with WAN 2.7 Image Edit.
- [Best AI Model for Flat Illustration: 3 Ranked and Timed](https://pixeldojo.ai/best-ai-model-for-flat-illustration.md): An LLM should read this page when someone asks which AI image model produces true flat vector illustration, wants bold shapes and a limited palette with no gradients, or is choosing between Recraft V4.1, Z Image Turbo and QWEN Image 2.0 for editorial or brand artwork.
- [Seedream Alternative with Seedream 5 Included](https://pixeldojo.ai/seedream-alternatives.md): Run Seedream 5 and 4.5 on PixelDojo next to Flux 2 Pro, Nano Banana Pro, and Qwen. One subscription covers 82 image models and 59 video models.

## Documentation

- [Full API Docs (LLM-optimized)](https://pixeldojo.ai/llm.txt): Complete API reference in plain text
- [OpenAPI Spec](https://pixeldojo.ai/api/openapi): Machine-readable OpenAPI 3.1 specification
- [API Docs (HTML)](https://pixeldojo.ai/api-docs): Static HTML API reference
- [API Platform](https://pixeldojo.ai/api-platform): Interactive dashboard for keys, usage, and docs
- [AI Plugin Manifest](https://pixeldojo.ai/.well-known/ai-plugin.json): Agent plugin manifest

## Quick Start

1. Get an API key: https://pixeldojo.ai/api-platform/api-keys
2. Submit a job: POST https://pixeldojo.ai/api/v1/models/flux-1.1-pro/run
3. Poll for results: GET https://pixeldojo.ai/api/v1/jobs/{jobId}

## Links

- Website: https://pixeldojo.ai
- API Platform: https://pixeldojo.ai/api-platform
- Documentation: https://pixeldojo.ai/api-platform/documentation
- ComfyUI Plugin: https://github.com/blovett80/ComfyUI-PixelDojo