Skip to main content

UNLIMITED

Flux 3 Klein, H3 Image, Qwen 2.1, MiniMax H3 Video, 310+ effectsSee plans

WAN 3.0 at 1080p now costs 40% less!! 15 credits @ 5 seconds instead of 25.

Available Models

156 AI models for image, video and audio generation behind one async control plane

88Images|65Videos
video

Brand Overlays

2 credits

Add a hook title, a lower-third callout, a review card, a progress bar, a countdown timer, a price tag, an offer badge and a branded end card to any video. Exact text in your brand color.

/api/v1/models/brand-overlay/run
View Docs
image

Bria Fibo 2.0

1 credit

Bria FIBO 2.0: text-to-image trained only on licensed data, with precise control over lighting, camera, composition and color. 21 aspect ratios at 1K, nine at 2K, plus image editing with up to 4 references.

/api/v1/models/bria-fibo-2/run
text-to-imageimage-to-image
View Docs
Change Camera Angle example output
image

Change Camera Angle

1 credit

Camera-aware editing via Qwen Image Edit with multi-angle LoRA. 360° orbit, tilt, and zoom.

/api/v1/models/change-camera-angle/run
image-to-image
View Docs
Clarity Pro example output
image

Clarity Pro

4 credits

Clarity Pro Upscaler via Replicate. Photorealistic upscaling with identity preservation and creative control. Up to 16× and 64 megapixels.

/api/v1/models/clarity-pro-upscaler/run
image-to-image
View Docs
Consistent Characters example output
image

Consistent Characters

1.25 credits

Generate consistent character variations with FLUX Kontext, Nano Banana Pro/2, Flux 2 Dev, Qwen Image 2 Pro, or Grok Imagine.

/api/v1/models/consistent-characters/run
image-to-image
View Docs
Creative Upscaler example output
image

Creative Upscaler

2.5 credits

Clarity Upscaler (creative upscale) via Replicate. Boost detail with stable-diffusion refinement.

/api/v1/models/creative-upscale/run
image-to-image
View Docs
Ernie example output
image

Ernie

1 credit

Baidu Ernie text-to-image. Multilingual prompts and built-in prompt expansion.

/api/v1/models/ernie/run
text-to-image
View Docs
Portrait Upscaler example output
image

Portrait Upscaler

6 credits

Crystal Upscaler via Replicate. Face-detail preserving upscale, cost scales with output megapixels.

/api/v1/models/face-enhance/run
image-to-image
View Docs
image

Face Swap

0.25 credits

Swap a face, or the entire head including hair, from one photo into another while preserving pose, lighting, and background.

/api/v1/models/face-swap/run
image-to-image
View Docs
FLUX example output
image

FLUX

1 credit

FLUX family on Replicate. Schnell, Dev, Pro, Kontext, Ultra, and LoRA remix variants in one entrypoint.

/api/v1/models/flux/run
text-to-imageimage-to-image
View Docs
Flux 2 Flex example output
image

Flux 2 Flex

2 credits

Max-quality with up to 10 reference images

/api/v1/models/flux-2-flex/run
text-to-imageimage-to-image
View Docs
Flux 2 Klein 4B example output
image

Flux 2 Klein 4B

0.1 credits

Very fast generation and editing with up to 5 reference images

/api/v1/models/flux-2-klein-4b/run
text-to-imageimage-to-image
View Docs
Flux 2 Klein 9B example output
image

Flux 2 Klein 9B

0.5 credits

4-step distilled FLUX.2 [klein] foundation model for flexible control

/api/v1/models/flux-2-klein-9b/run
text-to-imageimage-to-image
View Docs
Flux 2 Pro example output
image

Flux 2 Pro

1.5 credits

High-quality with up to 8 reference images

/api/v1/models/flux-2-pro/run
text-to-imageimage-to-image
View Docs
Flux 2 Max example output
image

Flux 2 Max

2.5 credits

The highest fidelity image model from Black Forest Labs

/api/v1/models/flux-2-max/run
text-to-imageimage-to-image
View Docs
Flux 2 Dev example output
image

Flux 2 Dev

1 credit

Fast quality with up to 4 reference images

/api/v1/models/flux-2-dev/run
text-to-imageimage-to-image
View Docs
Flux 2 Klein 9B + LoRA example output
image

Flux 2 Klein 9B + LoRA

1 credit

Klein 9B with custom LoRA support and up to 5 reference images

/api/v1/models/flux-2-lora/run
text-to-imageimage-to-image
View Docs
image

Flux 2 Dev + LoRA

1 credit

Flux 2 Dev with your own FLUX.2 [dev] LoRAs and up to 4 reference images

/api/v1/models/flux-2-dev-lora/run
text-to-imageimage-to-image
View Docs
FLUX 3 Image example output
image

FLUX 3 Image

1 credit

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.

/api/v1/models/flux-3-image/run
text-to-imageimage-to-image
View Docs
FLUX 3 Image Klein example output
image

FLUX 3 Image Klein

0.5 credits

FLUX 3 Image Klein: fast open-weights FLUX 3 for text-to-image and edits with up to 10 reference images, unlimited on Relax.

/api/v1/models/flux-3-image-klein/run
text-to-imageimage-to-image
View Docs
FLUX 3 Video example output
video

FLUX 3 Video

25 credits

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.

/api/v1/models/flux-3-video/run
text-to-videoimage-to-videovideo-extend
View Docs
Flux Edit (Kontext) example output
image

Flux Edit (Kontext)

1 credit

Black Forest Labs FLUX.1 Kontext for text-driven image editing. Dev (open-weight), Pro (state-of-the-art), and Max (premium typography).

/api/v1/models/flux-edit/run
image-to-image
View Docs
Flux Dev example output
image

Flux Dev

1 credit

High-quality development model with configurable steps and guidance. For LoRAs, use Flux Dev Multi LoRA.

/api/v1/models/flux-dev/run
text-to-image
View Docs
Flux Krea Dev example output
image

Flux Krea Dev

1 credit

Photorealistic generation that avoids the oversaturated AI look. Supports a single LoRA via lora_weights.

/api/v1/models/flux-krea-dev/run
text-to-image
View Docs
Flux Dev Multi LoRA example output
image

Flux Dev Multi LoRA

1 credit

Flux Dev with multiple stacked custom LoRAs for complex style combinations.

/api/v1/models/flux-dev-multi-lora/run
text-to-image
View Docs
Flux 1.1 Pro example output
image

Flux 1.1 Pro

1 credit

Latest pro model with enhanced quality and strong prompt adherence.

/api/v1/models/flux-1.1-pro/run
text-to-image
View Docs
Flux 1.1 Pro Ultra example output
image

Flux 1.1 Pro Ultra

1.5 credits

Highest quality Flux model with raw mode for natural-looking images.

/api/v1/models/flux-1.1-pro-ultra/run
text-to-image
View Docs
Flux Kontext Pro example output
image

Flux Kontext Pro

1 credit

Advanced model with state-of-the-art performance for both generation and editing.

/api/v1/models/flux-kontext-pro/run
text-to-imageimage-to-image
View Docs
Flux Kontext Max example output
image

Flux Kontext Max

2 credits

Premium model with maximum performance and improved typography for generation and editing.

/api/v1/models/flux-kontext-max/run
text-to-imageimage-to-image
View Docs
Google Gemini Flash example output
image

Google Gemini Flash

1 credit

Fast generation with Gemini 2.5 Flash

/api/v1/models/gemini-flash/run
text-to-image
View Docs
Google Nano Banana Pro example output
image

Google Nano Banana Pro

4.5 credits

SOTA with accurate typography and reasoning

/api/v1/models/nano-banana-pro/run
text-to-image
View Docs
Google Nano Banana 2 example output
image

Google Nano Banana 2

2.25 credits

Next-generation SOTA model with stronger consistency

/api/v1/models/nano-banana-2/run
text-to-image
View Docs
Google Nano Banana 2.1 example output
image

Google Nano Banana 2.1

1 credit

Sharper layouts and subject consistency, with more precise edits

/api/v1/models/nano-banana-2-1/run
text-to-image
View Docs
Google Nano Banana 2 Lite example output
image

Google Nano Banana 2 Lite

2 credits

Faster, lower-cost Nano Banana 2 at fixed 1K resolution

/api/v1/models/nano-banana-2-lite/run
text-to-image
View Docs
Gemini Omni Flash 1.2 example output
video

Gemini Omni Flash 1.2

24 credits

Google Gemini Omni Flash 1.2: text, frames, references, or a source video into 3–15s clips with native audio at 360p to 4K. First/last frame, reference images and videos, edit or extend a clip.

/api/v1/models/google-gemini-omni-flash/run
text-to-videoimage-to-video
View Docs
Nano Banana Edit example output
image

Nano Banana Edit

4.5 credits

Google Nano Banana image editing. Multi-image fusion + edit instruction with Standard/Pro/Pro-fal tiers; 1K/2K/4K on the Pro tiers, fixed 1K on Standard.

/api/v1/models/google-nano-banana/run
image-to-image
View Docs
GPT Image 2 example output
image

GPT Image 2

5 credits

OpenAI GPT Image 2: next-generation image model with 4K rendering and sharper text fidelity.

/api/v1/models/gpt-image-2/run
text-to-image
View Docs
GPT Image 2.6 example output
image

GPT Image 2.6

2 credits

OpenAI GPT Image 2.6 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.

/api/v1/models/gpt-image-2-5/run
text-to-imageimage-to-image
View Docs
GPT Image 2 Edit example output
image

GPT Image 2 Edit

5 credits

OpenAI GPT Image 2 image editing. Supply 1-8 reference images plus an edit instruction. 4K-capable; pricing varies by quality + size.

/api/v1/models/gpt-image-2-edit/run
image-to-image
View Docs
Grok R2V example output
video

Grok R2V

10 credits

xAI Grok Imagine reference-to-video via Replicate. 1 to 7 reference images plus prompt for 1 to 10 second clips at 480p or 720p.

/api/v1/models/grok-r2v/run
image-to-video
View Docs
Grok Video Extend example output
video

Grok Video Extend

1.5 credits/sec

xAI Grok Imagine video extension. Continue an existing MP4 with a prompt-directed extension (2 to 10 seconds).

/api/v1/models/grok-video-extend/run
video-extend
View Docs
Happy Horse Reference example output
video

Happy Horse Reference

4 credits/sec

Alibaba 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.

/api/v1/models/happyhorse-1.0-r2v/run
image-to-video
View Docs
Happy Horse 1.0 Text-to-Video example output
video

Happy Horse 1.0 Text-to-Video

4 credits/sec

Text-to-video with 720p/1080p output and 3-15 second durations

/api/v1/models/happyhorse-1.0-t2v/run
text-to-video
View Docs
Happy Horse 1.0 Image-to-Video example output
video

Happy Horse 1.0 Image-to-Video

4 credits/sec

Image-to-video animation with 720p/1080p output and 3-15 second durations

/api/v1/models/happyhorse-1.0-i2v/run
image-to-video
View Docs
Happy Horse Video Edit example output
video

Happy Horse Video Edit

5 credits/sec

Alibaba 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.

/api/v1/models/happyhorse-1.0-video-edit/run
image-to-video
View Docs
video

HeyGen Video 1.0

6.25 credits

HeyGen Video 1.0 via Runware. Text-to-video or image-to-video with sound built in: spoken dialogue, ambience and effects. 5 to 30 seconds, 480p to 2K.

/api/v1/models/heygen-video/run
text-to-videoimage-to-video
View Docs
Hunyuan Image 3 example output
image

Hunyuan Image 3

2 credits

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.

/api/v1/models/hunyuan-image-3/run
text-to-image
View Docs
Ideogram 4.5 example output
image

Ideogram 4.5

2 credits

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.

/api/v1/models/ideogram-4-5/run
text-to-imageimage-to-image
View Docs
Image to Image example output
image

Image to Image

1 credit

FLUX Dev LoRA image-to-image on Replicate. Prompt + source image + optional LoRA weights.

/api/v1/models/image-to-image-flux/run
image-to-image
View Docs
Kling 4.0 example output
video

Kling 4.0

25 credits

Kling Video 4.0. Up to 30 seconds at 1080p with native audio and dialogue: text, start/end frames, reference images and videos, or edit an existing clip. Flash tier: faster and cheaper at 720p, up to 20 seconds.

/api/v1/models/kling-4-0/run
text-to-videoimage-to-video
View Docs
video

Kling Avatar

2 credits/sec

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.

/api/v1/models/kling-avatar/run
image-to-video
View Docs
Kling Image example output
image

Kling Image

1 credit

Kling Image V3. High-quality text-to-image with flexible aspect ratios.

/api/v1/models/kling-image/run
text-to-image
View Docs
image

Kling Image 4

1.75 credits

Kling IMAGE 4.0: native 2K, 4K and 8K images with sharp text in seven languages, consistent series of up to 10 images, and full product pages or website designs from one prompt. Up to 10 reference images.

/api/v1/models/kling-image-4/run
text-to-imageimage-to-image
View Docs
Kling Image Edit example output
image

Kling Image Edit

1 credit

Kling Image V3 image-to-image editing with a text instruction.

/api/v1/models/kling-image-edit/run
image-to-image
View Docs
Kling Motion Control v3 Standard example output
video

Kling Motion Control v3 Standard

3 credits/sec

Kling Video v3 Standard motion control (720p)

/api/v1/models/kling-motion-control/run
image-to-video
View Docs
Kling Motion Control v3 Pro example output
video

Kling Motion Control v3 Pro

4 credits/sec

Kling Video v3 Pro motion control (1080p)

/api/v1/models/kling-motion-control-pro/run
image-to-video
View Docs
Kling Reference to Video example output
video

Kling Reference to Video

15 credits

Kling reference-driven video generation. Image or video references, Standard or Pro tier.

/api/v1/models/kling-reference-to-video/run
image-to-videovideo-extend
View Docs
Kling 2.6 Pro example output
video

Kling 2.6 Pro

25 credits

Kling Video v2.6 Pro. Text-to-video or image-to-video, 5 or 10 seconds, with audio generation.

/api/v1/models/kling-v2-6/run
text-to-videoimage-to-video
View Docs
Kling Video v3 Standard (Text) example output
video

Kling Video v3 Standard (Text)

4 credits/sec

Standard text-to-video with native audio

/api/v1/models/kling-video-v3-standard-text/run
text-to-video
View Docs
Kling Video v3 Standard (Image) example output
video

Kling Video v3 Standard (Image)

4 credits/sec

Standard image-to-video with native audio

/api/v1/models/kling-video-v3-standard-image/run
image-to-video
View Docs
Kling Video v3 Pro (Text) example output
video

Kling Video v3 Pro (Text)

5.5 credits/sec

Pro text-to-video with cinematic quality and native audio

/api/v1/models/kling-video-v3-pro-text/run
text-to-video
View Docs
Kling Video v3 Pro (Image) example output
video

Kling Video v3 Pro (Image)

5.5 credits/sec

Pro image-to-video with cinematic quality and native audio

/api/v1/models/kling-video-v3-pro-image/run
image-to-video
View Docs
Kling Video Edit example output
video

Kling Video Edit

28 credits

Kling video-to-video edit. Standard or Pro, with optional reference images and audio preservation.

/api/v1/models/kling-video-edit/run
video-extend
View Docs
image

Krea 3

1.5 credits

Krea 3 for reference-driven images and edits. Start from up to 8 images, describe the change and keep the parts you like, or generate from a prompt alone. Up to 4K in 10 aspect ratios.

/api/v1/models/krea-3/run
text-to-imageimage-to-image
View Docs
Krea Image example output
image

Krea Image

0.5 credits

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.

/api/v1/models/krea-v2/run
text-to-image
View Docs
video

Luma Ray3.2

10 credits

Luma Ray3.2 video via Runware. Text-to-video, or image-to-video with a start frame and an optional end frame. 5 or 10 seconds, 360p to 1080p, silent.

/api/v1/models/luma-ray-3-2/run
text-to-videoimage-to-video
View Docs
Luma UNI 1 example output
image

Luma UNI 1

1 credit

Luma UNI 1 (Standard + MAX) via Runware. Text-to-image and reference-guided image editing with one prompt, two quality tiers.

/api/v1/models/luma-uni-1/run
text-to-imageimage-to-image
View Docs
Magnific Upscaler example output
image

Magnific Upscaler

3 credits

Freepik Magnific upscaler. Creative or precision mode, up to 16x.

/api/v1/models/magnific-upscaler/run
image-to-image
View Docs
MiniMax H3 example output
video

MiniMax H3

4 credits/sec

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).

/api/v1/models/minimax-h3/run
text-to-videoimage-to-video
View Docs
video

MiniMax H3 Max

2 credits/sec

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.

/api/v1/models/minimax-h3-max/run
text-to-videoimage-to-video
View Docs
video

MiniMax H3 Max Turbo

1.25 credits/sec

MiniMax H3 Max Turbo, the distilled, faster H3 Max. Text-to-video and image-to-video at 768p (1.25 credits/sec) or 480p (0.9 credits/sec), 5-15s, native synced audio. No reference inputs.

/api/v1/models/minimax-h3-max-turbo/run
text-to-videoimage-to-video
View Docs
video

MiniMax H3 Fast

1.5 credits/sec

MiniMax H3 Fast, the speed-optimized H3. Text-to-video, image-to-video and reference-to-video (images, video and audio references) at 480p, 1.5 credits/sec plus 1.75 credits per second of reference video (at most 15s) and 1 per reference image past the fifth, 5-15s, native synced audio.

/api/v1/models/minimax-h3-fast/run
text-to-videoimage-to-video
View Docs
image

MiniMax H3 Image

1.5 credits

MiniMax H3 Image: natural photoreal images up to 16 MP that follow long, detailed prompts closely, with accurate text, and edits from up to 8 images.

/api/v1/models/minimax-h3-image/run
text-to-imageimage-to-image
View Docs
video

MiniMax H3 Turbo

7.5 credits

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.

/api/v1/models/minimax-h3-turbo/run
text-to-videoimage-to-video
View Docs
image

Muse Image

0.5 credits

Meta's Muse Image: text-to-image at 2K in 8 aspect ratios, plus editing and multi-reference composition with up to 10 reference images.

/api/v1/models/muse-image/run
text-to-imageimage-to-image
View Docs
OmniHuman example output
video

OmniHuman

5 credits/sec

ByteDance OmniHuman 2.0. Audio-driven talking-head video with lip sync, up to 2 minutes.

/api/v1/models/omnihuman/run
audio-to-videoimage-to-video
View Docs
Image Outpainting example output
image

Image Outpainting

1 credit

Outpainting. Expand an image beyond its original edges.

/api/v1/models/outpaint/run
outpainting
View Docs
image

P-H3-Image

1 credit

P-H3-Image: open-weights image model built from MiniMax H3. Photoreal, editorial and film-still looks up to 8 MP, short quoted text, and edits from up to 8 images.

/api/v1/models/p-h3-image/run
text-to-imageimage-to-image
View Docs
P-Image example output
image

P-Image

0.1 credits

Pruna P-Image. Sub-second text-to-image with optional custom dimensions.

/api/v1/models/p-image/run
text-to-image
View Docs
P-Image Edit example output
image

P-Image Edit

0.25 credits

Pruna P-Image Edit. Fast image editing with up to 5 reference images.

/api/v1/models/p-image-edit/run
image-to-image
View Docs
P-Image Ideogram example output
image

P-Image Ideogram

0.5 credits

Ideogram-class text rendering on the Pruna backbone. Pick a thinking budget from 0.1 to 1 credit per image.

/api/v1/models/p-image-ideogram/run
text-to-image
View Docs
P-Image Upscale example output
image

P-Image Upscale

0.1 credits

Pruna P-Image Upscale. Fast image upscaling to a target megapixel size, with optional detail and realism enhancement.

/api/v1/models/p-image-upscale/run
image-to-image
View Docs
P-Video example output
video

P-Video

0.75 credits/sec

Pruna P-Video 2 (and P-Video 1): video generation with text/image/audio conditioning, draft mode, and 720p/1080p outputs.

/api/v1/models/p-video/run
text-to-videoimage-to-videoaudio-to-video
View Docs
video

P-Video 2 Pro

1 credit/sec

Pruna P-Video 2 Pro: text or image to video with generated audio, 5 to 15 seconds at 24 fps, with start and end frame control.

/api/v1/models/p-video-2-pro/run
text-to-videoimage-to-video
View Docs
video

P-Video 2 Pro Reference

1.25 credits/sec

Pruna P-Video 2 Pro Reference: reference-to-video built on MiniMax H3. Up to 9 images, 3 video and 3 audio references, plus optional start and end frames, 480p or 768p, 5 to 15 seconds with native audio. keep_audio lip-syncs to your own song or line.

/api/v1/models/p-video-2-pro-reference/run
image-to-video
View Docs
video

P-Video 2 Pro Replace

3 credits/sec

Pruna P-Video 2 Pro Replace, built on MiniMax H3: swap one or two people in a video for the people in your pictures. Motion, camera, background, everyone else and the sound stay as they were. Up to 120 seconds, 480p or 768p.

/api/v1/models/p-video-2-pro-replace/run
image-to-video
View Docs
P-Video Avatar example output
video

P-Video Avatar

1 credit/sec

Pruna P-Video 2 Pro Avatar: animate a portrait into a talking avatar from a script or an audio file, up to 3 minutes. 30 voices, 10 languages, 480p to 4K.

/api/v1/models/p-video-avatar/run
image-to-video
View Docs
video

P-Video Edit

2 credits/sec

Pruna P-Video Edit: prompted edits on a clip up to 15 seconds, with up to 4 reference images. Keeps the original audio; draft mode for quick previews.

/api/v1/models/p-video-edit/run
image-to-video
View Docs
video

P-Video Upscale

0.6 credits/sec

Pruna P-Video Upscale. Fast, low-cost video upscaling to 720p, 1080p, 2K, or 4K. Keeps the aspect ratio and the original audio.

/api/v1/models/p-video-upscale/run
View Docs
PixVerse V6 example output
video

PixVerse V6

10 credits

Pixverse V6 video generation via Runware. Text-to-video, image-to-video (start frame), or multi-clip (start + end frame).

/api/v1/models/pixverse-v6/run
text-to-videoimage-to-video
View Docs
Pony Realism example output
image

Pony Realism

1 credit

Pony Realism - Stylized anime generation

/api/v1/models/ponyxl-ponyrealism-v23/run
text-to-imageimage-to-image
View Docs
Pony NAI example output
image

Pony NAI

1 credit

Pony NAI - Stylized anime generation

/api/v1/models/ponyxl-tponynai3-v7/run
text-to-imageimage-to-image
View Docs
Wai ANI example output
image

Wai ANI

1 credit

Wai ANI - Stylized anime generation

/api/v1/models/ponyxl-waianinsfwponyxl-v140/run
text-to-imageimage-to-image
View Docs
Qwen 3 Pro example output
image

Qwen 3 Pro

1 credit

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.

/api/v1/models/qwen-3-pro/run
text-to-imageimage-to-image
View Docs
Qwen Image Plus example output
image

Qwen Image Plus

1 credit

Fast generation with excellent quality

/api/v1/models/qwen-image-plus/run
text-to-image
View Docs
Qwen Image Max example output
image

Qwen Image Max

2 credits

Highest quality output

/api/v1/models/qwen-image-max/run
text-to-image
View Docs
Qwen Image 2.0 example output
image

Qwen Image 2.0

0.5 credits

Fast, balanced image generation and editing

/api/v1/models/qwen-image-2.0/run
text-to-image
View Docs
Qwen Image 2.0 Pro example output
image

Qwen Image 2.0 Pro

1.5 credits

Enhanced text rendering, realistic textures, and semantic adherence

/api/v1/models/qwen-image-2.0-pro/run
text-to-image
View Docs
image

Qwen Image 2.1 Turbo

0.5 credits

8-step distilled checkpoint: fast native-2K images and edits

/api/v1/models/qwen-image-2.1-turbo/run
text-to-imageimage-to-image
View Docs
Qwen Image 2.1 example output
image

Qwen Image 2.1

1.5 credits

Full 40-step checkpoint: the most detail and the best typography

/api/v1/models/qwen-image-2.1/run
text-to-imageimage-to-image
View Docs
Qwen Image 2 Edit example output
image

Qwen Image 2 Edit

0.5 credits

Alibaba DashScope Qwen Image 2 edit. Supply 1-3 reference images plus an edit instruction. Standard and Pro variants.

/api/v1/models/qwen-image-2-edit/run
image-to-image
View Docs
Qwen Image Edit example output
image

Qwen Image Edit

1 credit

Alibaba DashScope Qwen Image edit. Supply 1-3 reference images plus an edit instruction. Plus and Max model variants.

/api/v1/models/qwen-image-edit/run
image-to-image
View Docs
Qwen Image Edit Realistic example output
image

Qwen Image Edit Realistic

1 credit

Qwen Image Edit, Realistic mode. Add, remove, or modify elements in an existing image with text guidance.

/api/v1/models/qwen-image-edit-spicy/run
image-to-image
View Docs
Recraft V4.1 example output
image

Recraft V4.1

1 credit

Recraft's latest image model. Better photorealism, smoother gradients, and improved text rendering vs V4. ~1024px output.

/api/v1/models/recraft-v4.1/run
text-to-image
View Docs
Recraft V4.1 Pro example output
image

Recraft V4.1 Pro

5 credits

V4.1 at ~2048px resolution. Print-ready and large-scale work with the same prompt accuracy and design taste as standard.

/api/v1/models/recraft-v4.1-pro/run
text-to-image
View Docs
Recraft V4.1 SVG example output
image

Recraft V4.1 SVG

1 credit

Production-ready SVG vector output. Clean geometry, structured layers, editable paths. V4.1's design taste applied to vector.

/api/v1/models/recraft-v4.1-svg/run
text-to-image
View Docs
Recraft V4.1 Pro SVG example output
image

Recraft V4.1 Pro SVG

5 credits

Detailed SVG vector graphics with finer paths and more geometric detail than standard SVG.

/api/v1/models/recraft-v4.1-pro-svg/run
text-to-image
View Docs
Riverflow example output
image

Riverflow

1 credit

Sourceful Riverflow 2.0 (Fast + Pro) via Runware. 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.

/api/v1/models/riverflow/run
text-to-image
View Docs
Rodin example output
image

Rodin

12 credits

Hyper3D Rodin. Turn up to 5 reference images into production-ready 3D models, with fast and standard quality modes.

/api/v1/models/rodin/run
View Docs
video

Runway Gen-4.5

20 credits

Runway's Gen-4.5 video model. Text-to-video or image-to-video at 720p in five shapes, 5, 8 or 10 seconds, with cinematic camera work and believable motion. Clips are silent.

/api/v1/models/runway-gen-4-5/run
text-to-videoimage-to-video
View Docs
Audio

Seed Audio 1.0

0.1 credits/sec

ByteDance Seed Audio 1.0. Generate speech, voice clones, and full audio scenes (radio dramas, podcasts, narration) from a prompt.

/api/v1/models/seed-audio/run
View Docs
Seedance 2 High example output
video

Seedance 2 High

6 credits/sec

Higher-quality Seedance 2.0 video generation (supports 1080p)

/api/v1/models/seedance-2-high/run
text-to-videoimage-to-video
View Docs
video

Seedance 2 Mini

2 credits/sec

Cost-effective Seedance 2.0 Mini. Same creation flow at roughly half the credits (480p / 720p)

/api/v1/models/seedance-2-mini/run
text-to-videoimage-to-video
View Docs
Seedance 2.5 example output
video

Seedance 2.5

6 credits/sec

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.

/api/v1/models/seedance-2-5/run
text-to-videoimage-to-video
View Docs
video

Seedance 2.5 Flash

4 credits/sec

Seedance 2.5 Flash: the faster, lower-cost Seedance 2.5. Text-to-video, first/last frame, and reference-to-video, up to 30 seconds at 480p or 720p with native audio.

/api/v1/models/seedance-2-5-flash/run
text-to-videoimage-to-video
View Docs
video

Seedance 2.5 Video Edit

4.5 credits/sec

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.

/api/v1/models/seedance-2-5-video-edit/run
image-to-video
View Docs
Seedance 2 Reference example output
video

Seedance 2 Reference

20 credits

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.

/api/v1/models/seedance-2-reference/run
image-to-video
View Docs
Seedance 2 Video Edit example output
video

Seedance 2 Video Edit

25 credits

Edit source videos with Seedance 2.0 using prompted changes, optional reference images, and 480p, 720p, or 1080p output.

/api/v1/models/seedance-video-edit/run
text-to-videoimage-to-video
View Docs
Seedream 4.5 example output
image

Seedream 4.5

1.25 credits

ByteDance Seedream 4.5: new-generation image creation with superior aesthetics, text rendering, and up to 4K resolution.

/api/v1/models/seedream-4/run
text-to-imageimage-to-image
View Docs
Seedream 5 example output
image

Seedream 5

2.75 credits

Seedream 5 Pro: the flagship Seedream image model with sharper realism, stronger prompt adherence, and best-in-class text rendering.

/api/v1/models/seedream-5/run
text-to-imageimage-to-image
View Docs
image

Seedream 5.5

1 credit

Seedream 5.5: the newest Seedream image model. Sharp, realistic images in seconds, exact text, edits that keep the subject the same, and transparent backgrounds.

/api/v1/models/seedream-5-5/run
text-to-imageimage-to-image
View Docs
image

Seedream 5 Flash

0.5 credits

Seedream 5 Flash: the fast, low-cost Seedream 5 model for quick drafts and high-volume image generation and editing.

/api/v1/models/seedream-5-flash/run
text-to-imageimage-to-image
View Docs
Seedream 5 Lite example output
image

Seedream 5 Lite

1 credit

ByteDance Seedream 5.0 Lite: fast, high-quality image generation and editing with strong aesthetics and text rendering.

/api/v1/models/seedream-5-lite/run
text-to-imageimage-to-image
View Docs
Audio

Text to Music

6 credits

ACE-Step v1.5. Generate instrumental beds or full songs from a prompt, 30 seconds to 5 minutes.

/api/v1/models/text-to-music/run
View Docs
Audio

Text to Speech

0.5 credits

MiniMax Speech 2.8 Turbo via Replicate. Convert text into natural-sounding speech.

/api/v1/models/text-to-speech/run
View Docs
Veo 3.1 Fast example output
video

Veo 3.1 Fast

4.5 credits/sec

Faster generation at 4.5 credits per second with native audio (3 with generate_audio false)

/api/v1/models/veo-3.1-fast/run
text-to-videoimage-to-video
View Docs
Veo 3.1 Standard example output
video

Veo 3.1 Standard

12 credits/sec

Higher quality at 12 credits per second with native audio (8 with generate_audio false)

/api/v1/models/veo-3.1-standard/run
text-to-videoimage-to-video
View Docs
Veo 3.1 Lite example output
video

Veo 3.1 Lite

2 credits/sec

Runware-powered 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.

/api/v1/models/veo-3.1-lite/run
text-to-videoimage-to-video
View Docs
Video Autocaption example output
video

Video Autocaption

5 credits

Animated word-by-word captions, placed clear of the TikTok, Reels and Shorts buttons.

/api/v1/models/video-autocaption/run
View Docs
Video Upscaler example output
video

Video Upscaler

5 credits

FlashVSR video upscaling. Enhance video resolution up to 4K.

/api/v1/models/video-upscaler/run
View Docs
WAN 2.1 Video example output
video

WAN 2.1 Video

2.5 credits/sec

WAN 2.1 (14B) text & image to video with LoRA support. 480p/720p, 1-5 second clips.

/api/v1/models/wan-2.1-video/run
text-to-videoimage-to-video
View Docs
WAN 2.2 Standard example output
video

WAN 2.2 Standard

3 credits

Premium quality with enhanced detail

/api/v1/models/wan-2.2-standard/run
text-to-videoimage-to-video
View Docs
WAN 2.2 Plus example output
video

WAN 2.2 Plus

3 credits

Official Alibaba model with 1080p support

/api/v1/models/wan-2.2-plus/run
image-to-video
View Docs
WAN 2.2 Image-to-Video example output
video

WAN 2.2 Image-to-Video

5 credits

Image-to-video with WAN 2.2. Animate a starting image. 480p or 720p, 5s or 8s clips.

/api/v1/models/wan-2.2-i2v-spicy/run
image-to-video
View Docs
WAN 2.2 Replace example output
video

WAN 2.2 Replace

10 credits

WAN 2.2 character replacement. Swap a character in a source video while preserving scene and motion.

/api/v1/models/wan-2.2-replace/run
image-to-video
View Docs
WAN 2.6 Standard example output
video

WAN 2.6 Standard

2 credits/sec

Higher quality, 720p/1080p support

/api/v1/models/wan-2.6-standard/run
text-to-videoimage-to-video
View Docs
WAN 2.6 Flash example output
video

WAN 2.6 Flash

1.5 credits/sec

Fast and affordable image-to-video

/api/v1/models/wan-2.6-flash/run
image-to-video
View Docs
WAN 2.6 Image example output
image

WAN 2.6 Image

1 credit

Alibaba WAN 2.6 text-to-image with prompt enhancement and multi-image output.

/api/v1/models/wan-2.6-image/run
text-to-image
View Docs
WAN 2.6 Image Edit example output
image

WAN 2.6 Image Edit

1 credit

Alibaba WAN 2.6 image editing. Up to 4 reference images.

/api/v1/models/wan-2.6-image-edit/run
image-to-image
View Docs
WAN 2.7 Image-to-Video example output
video

WAN 2.7 Image-to-Video

12.5 credits

Image-to-video with WAN 2.7. Animate a starting image with optional driving audio. 720p or 1080p, 2–15 second clips.

/api/v1/models/wan-2.7-i2v-spicy/run
image-to-video
View Docs
WAN 2.7 Standard example output
image

WAN 2.7 Standard

0.6 credits

Faster Wan 2.7 image generation and editing

/api/v1/models/wan-2.7-image/run
text-to-imageimage-to-image
View Docs
WAN 2.7 Pro example output
image

WAN 2.7 Pro

1.5 credits

Higher quality Wan 2.7 tier with 4K support for text-to-image

/api/v1/models/wan-2.7-image-pro/run
text-to-imageimage-to-image
View Docs
WAN 2.7 Image Edit example output
image

WAN 2.7 Image Edit

0.6 credits

Alibaba WAN 2.7 image editing. Standard and Pro tiers, supports up to 9 input images for fusion edits.

/api/v1/models/wan-2.7-image-edit/run
image-to-image
View Docs
WAN 2.7 Text-to-Video example output
video

WAN 2.7 Text-to-Video

2 credits/sec

Text-to-video with audio sync, 720p/1080p output, and 2-15 second durations

/api/v1/models/wan-2.7-t2v/run
text-to-video
View Docs
WAN 2.7 Image-to-Video example output
video

WAN 2.7 Image-to-Video

2 credits/sec

Image-to-video and video continuation with optional last-frame control and audio sync

/api/v1/models/wan-2.7-i2v/run
image-to-videovideo-extend
View Docs
WAN 3.0 example output
video

WAN 3.0

10 credits

Alibaba WAN 3.0 video. Text-to-video with optional reference images or first/last frame control, native audio, up to 30 seconds.

/api/v1/models/wan-3-0-video/run
text-to-videoimage-to-video
View Docs
WAN 2.2 Image example output
image

WAN 2.2 Image

1 credit

Fast cinematic image generation (3-6 seconds) with up to 2MP output and optional LoRA support.

/api/v1/models/wan-image/run
text-to-image
View Docs
WAN Reference to Video example output
video

WAN Reference to Video

4.5 credits/sec

Alibaba WAN reference-to-video. Up to 5 image/video references with multi-shot support.

/api/v1/models/wan-reference-to-video/run
image-to-video
View Docs
WAN Video Character Swap example output
video

WAN Video Character Swap

3.4 credits/sec

Alibaba WAN character swap. Combine a character image with a reference video to produce a new clip.

/api/v1/models/wan-video-character-swap/run
image-to-video
View Docs
WAN 2.7 Video Edit example output
video

WAN 2.7 Video Edit

6.5 credits/sec

Alibaba WAN 2.7 video editing. Modify an existing clip via prompt with optional reference images.

/api/v1/models/wan-video-edit/run
video-extend
View Docs
Grok Image example output
image

Grok Image

1 credit

xAI Grok Imagine. Fast tier for quick iteration, Quality tier for higher fidelity at 1k or 2k.

/api/v1/models/xai-image/run
text-to-image
View Docs
Grok Image Edit example output
image

Grok Image Edit

1 credit

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.

/api/v1/models/xai-image-edit/run
image-to-image
View Docs
Grok Video example output
video

Grok Video

7.5 credits

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.

/api/v1/models/xai-video/run
text-to-videoimage-to-video
View Docs
Grok Video Edit example output
video

Grok Video Edit

15 credits

xAI Grok Imagine Video edit. Transform short clips via Replicate.

/api/v1/models/xai-video-edit/run
video-extend
View Docs
Z Image Realistic example output
image

Z Image Realistic

1 credit

Z Image text-to-image, Realistic mode. Square / portrait / landscape compositions, 256–1536px on each side.

/api/v1/models/z-image-spicy/run
text-to-image
View Docs
Z-Image Turbo example output
image

Z-Image Turbo

0.25 credits

Super-fast 6B parameter text-to-image with great text rendering and LoRA support.

/api/v1/models/z-image-turbo/run
text-to-image
View Docs

Questions & Answers

Frequently Asked Questions

Authentication, pricing, async jobs, and output lifetime for the PixelDojo API

Quick start:

https://pixeldojo.ai/api/v1