logo
RunComfy
  • ComfyUI
  • Trainer
  • Models
  • MCPNew
  • Pricing
  • Seedance 2.5Hot
  • Seedream 5.5New

Workflows by Model

HotMiniMax H3Video with audio from text, images or referencesHotQwen Image 2.1Create images and edit photos with referencesWanVideo from text or images, motion transferFLUXImage generation, editing and character variationsLTXVideo with synced audio from text or imagesQwen Image EditPhoto editing with text and image referencesKrea 2Image creation, style transfer and reference editsZ-ImageFast portraits and concepts from text

Popular & New Workflows

NewMiniMax H3 Character Swap V1.5Swap video characters, keep the original audioNewP-H3-Image Reference EditEdit a photo guided by a reference imageHotMiniMax H3 Image-to-VideoOne image to cinematic video with synced audioHotLTX 2.5 Image-to-VideoOne frame to sharp video with synced audioHotMiniMax H3 Character Swap (SAM3)Swap video characters while following the motionQwen Image 2.1 Multi-Image EditingPrecise scenes from up to 10 reference imagesFLUX Klein Face SwapNatural, lifelike face swapsSeedVR2 Video UpscalerSharp, smooth video upscaling
View More Workflows

Train a Model

NewMOSS-Image BaseImage generation, newly supportedNewFLUX.3 KleinImage generation, newly supportedHotKrea 2The most-trained image modelHotKrea 2 TurboFew-step image generationHotQwen Image 2.1Image generation and editingZ-Image TurboFast portraits and concept imagesMiniMax H3Video with synchronized audio

Train & Deploy

Getting StartedYour first training job with Ostris AI ToolkitDatasetsUpload and manage training datasetsInferenceRun your trained models in a playground or via APIDeploymentsServe your trained models as dedicated endpoints
Train More Models

Image Models

NewGPT Image 2.65% OFF · Detailed text to image, GIF and SVG, up to 4KNewSeedream 5.510% OFF · Text to image up to 2K, with transparent PNGsNewMiniMax H3 Image10% OFF · Text or references to a still up to 4KNewFLUX 3 Image Klein10% OFF · Text or references to a still from 768 to 4KHotSeedream 5.0 Pro41% OFF · Reference edits with multilingual textHotSeedream 4.520% OFF · Photoreal edits with brand consistencyHotWan 2.6 ImageInstruction-based image editingNano Banana Pro77% OFF · Precise 2K to 4K visuals from sketches

Video Models

NewSeedance 2.5 Flash34% OFF · Text, image, or reference to videoNewKling 4.010% OFF · Animate a still into a 3 to 30s clipHotWan 3.0 Prime13% OFF · Fast clips from reference videosHotSeedance 2.536% OFF · Longer, more consistent cinematic videoHotWan 3.0Clips from image, video and audio referencesHotMiniMax H3Animate a first frame into a 5 to 15s clipWan 2.510% OFF · Fluid motion with native audioFLUX 3 MaxClips from text, a still, or keyframes
View More Models

API

Serverless (ComfyUI)Deploy ComfyUI workflows as serverless endpoints.Serverless (LoRA)Deploy LoRAs as serverless endpoints.Model APIRun hosted models on-demand with no deployment.Trainer APITrain, manage, and retrieve LoRAs via API.CLIRun RunComfy models from your terminal.
MODELS
Explore
All Models
LIBRARY
Generations
MODEL APIS
API Docs
API Keys
ACCOUNT
Usage

Qwen Image 3.0 Pro Edit: Image Editing on Models and API | RunComfy

qwen/qwen-image-3.0/pro/edit

Qwen Image 3.0 Pro Edit reworks an uploaded image from natural-language instructions with professional quality, 1K or 2K output, aspect-ratio control, prompt expansion, and seeds.

Image 1
One to three images to edit. The edit follows your instruction while keeping the rest of the picture.
Describe the change in plain language, e.g. what to add, remove, restyle, or replace. Quote any text to render it verbatim.
Output detail tier. Choose 1k for faster drafts or 2k for maximum detail.
The aspect ratio of the generated image.
Let the model enrich a short prompt with extra detail before generating. Turn off when your prompt is already precise.
Random seed for reproducibility. Use -1 for a random seed each run.
Idle
The rate is $0.038 per 1k output image and $0.072 per 2k output image, plus $0.0028 per input image.

Introduction To Qwen Image 3.0 Pro Edit

Qwen Image 3.0 Pro Edit is Qwen's professional editor that transforms an existing image from natural-language instructions at up to 2K.

Trading slow manual compositing for one written instruction, Qwen Image 3.0 Pro Edit helps studios, marketers, and developers restyle and refine visuals with production polish.

For developers, Qwen Image 3.0 Pro Edit on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.

Ideal for: High-End Retouching | Product Restaging | Brand & Campaign Edits

Parameters#


Qwen Image 3.0 Pro Edit takes one to three source images plus a written instruction and returns a polished Qwen Image 3.0 Pro Edit result. These controls shape each Qwen Image 3.0 Pro Edit run.


ParameterRequiredTypeDefaultRange / OptionsDescription
image_urls*Yes (*)ArraySample image1-3 imagesThe source image(s) to edit; the model keeps the rest of the picture.
prompt*Yes (*)StringExample instructionUp to ~4,500 tokensPlain-language edit instruction. Quote any text to render it verbatim.
resolutionNoString2k1k, 2kOutput detail tier: 1k or 2k.
aspect_ratioNoString1:11:1, 16:9, 9:16, 4:3, 3:4Output aspect ratio for the edited image.
enable_prompt_expansionNoBooleantruetrue, falseEnrich a short instruction before editing; turn off when it is already precise.
seedNoInteger-1-1 or 0-2147483647Fix a seed to reproduce an edit; use -1 for fresh variations.

  • Required field.

Pricing#


Qwen Image 3.0 Pro Edit is billed at $0.038 per 1K output image and $0.072 per 2K output image, plus $0.0028 per input image. For a batch, cost is the per-output rate times the number of outputs plus the input-image charge, so Qwen Image 3.0 Pro Edit only charges for what you generate.

Related Models

seedream-5/lite/edit

Transforms reference visuals into layout-accurate, style-consistent designs for creative workflows.

ideogram-v3/edit

Edit images by masking areas and prompting changes with Ideogram 3.

stepx-edit2

AI image editing from text with region control and brand consistency.

dreamina-4-0/edit

Generate 4K visuals with precise edits and style control for designers.

qwen-edit-2509/lora/multiple-angles

Multi-angle image editing with precision control and seamless visual consistency

gpt-image-2.6/flare/text-to-image

Fast text-to-image with legible in-image text, GIF and SVG, up to 4K.

Frequently Asked Questions

What does Qwen Image 3.0 Pro Edit do?

Qwen Image 3.0 Pro Edit is a professional image editor that transforms an uploaded image from a natural-language instruction at up to 2K. Describe the change - relight a scene, restage a product, refine a portrait, or restyle a shot - and Qwen Image 3.0 Pro Edit applies it with production-grade polish while keeping the rest coherent.

How is Qwen Image 3.0 Pro Edit different from the standard edit model?

Qwen Image 3.0 Pro Edit targets high-end, delivery-ready results with stronger detail and instruction understanding. Choose it for retouching, brand, and campaign work where finish quality matters; the standard edit model is a lighter, lower-cost option for everyday changes.

How many images can Qwen Image 3.0 Pro Edit take?

You can supply one to three source images. Qwen Image 3.0 Pro Edit reads them together, which helps when combining elements or keeping a subject consistent across an edit. Pair them with a clear instruction describing the intended result.

What output resolutions and aspect ratios are available?

Qwen Image 3.0 Pro Edit offers a 1K or 2K detail tier and aspect ratios of 1:1, 16:9, 9:16, 4:3, and 3:4. Use 1K for quick iterations and 2K for final delivery; check the current RunComfy panel for the exact options.

Can I reproduce an edit and control randomness?

Yes. Set a fixed seed to reproduce a Qwen Image 3.0 Pro Edit result with the same image and instruction, or use -1 for a fresh variation. An optional prompt expansion setting enriches short instructions before editing.

How much does Qwen Image 3.0 Pro Edit cost on RunComfy?

Qwen Image 3.0 Pro Edit is billed at $0.038 per 1K output image and $0.072 per 2K output image, plus $0.0028 for each input image. For a batch, the total is the per-output rate times the number of results plus the input-image charge.

Can developers call Qwen Image 3.0 Pro Edit through the API?

Yes. Prototype an edit in the RunComfy UI, then call the same Qwen Image 3.0 Pro Edit model via the RunComfy HTTP API with identical parameters. You do not need to host or scale the model yourself, and the same inputs produce comparable results.

Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Video Models
  • Seedance 2.5 Flash Text To Video
  • Seedance 2.5 Flash
  • Seedance 2.5 Flash Reference to Video
  • Wan 3.0
  • MiniMax H3 Fast
  • Wan 2.5
  • View All Models →
Image Models
  • Seedream 5.5
  • Seedream 5.5 Edit
  • Seedream 5.5 Layer Decomposition
  • Wan 2.6 Image to Image
  • Nano Banana Pro
  • Seedream 5.0 Pro
  • View All Models →
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Examples Of Qwen Image 3.0 Pro Edit