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 Pro20% 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 4.09% OFF · Animate a still into a 3 to 30s clipHotWan 3.0 Prime13% OFF · Fast clips from reference videosHotSeedance 2.535% 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

Wan 2.7 Pro: High-Fidelity AI Image Editing | RunComfy

wan-ai/wan-2.7/pro/edit

Run Wan 2.7 Pro image edits with full control fidelity: up to four ordered references, negative prompts, size presets, optional prompt expansion, and batched outputs—about $0.075 per image on RunComfy.

Image 1
Reference images for editing (1–4). Order matters: refer to image 1, image 2, image 3, image 4 in your prompt.
Text prompt describing the desired image edit. Supports Chinese and English.
Content to avoid in the generated image. Max 500 characters.
Output image size preset; mapped to the provider’s internal size format.
Number of images to generate (1–4). Default 1.
Enable DashScope prompt expansion (image edit mode). Default true.
Random seed for reproducibility (0–2147483647).
Idle
The rate is $0.075 per image.

Introduction To Wan 2.7 Pro Image Edit

Wan 2.7 Pro image edit targets the same instruction-based workflow as the standard editor—ordered reference images, bilingual prompts, optional automatic prompt expansion—but tuned for higher output fidelity suitable for print-ready product work and detailed style transfers. Use Pro when you need higher-resolution or more refined edits than the standard Wan 2.7 image edit model. On RunComfy the Pro route mirrors the non-Pro edit inputs (image_urls 1–4, prompt, negative_prompt, image_size, num_images, enable_prompt_expansion, seed, enable_safety_checker).

Ideal for: high-resolution retouching | premium lookbooks | packaging mock edits | intricate multi-reference fusion where standard edit lacks bite

Wan 2.7 Pro Image Edit#


Overview#


Wan 2.7 Pro image edit on RunComfy uses the same request shape as the standard edit route while targeting sharper, higher-fidelity results at a higher list price. Confirm output limits against the current RunComfy deployment.


Response fields#


The response includes images plus seed, matching the standard edit response shape.


Key features#


  • Pro quality target: Choose this route when standard Wan 2.7 edit is not enough for final delivery.
  • 1–4 image_urls: Use explicit “image 1” and “image 2” language in prompts.
  • enable_prompt_expansion: Helpful for sparse prompts; turn off for strict, deterministic art direction.
  • Safety and bilingual support match the standard edit route.

Parameters#

ParameterRequiredTypeDefaultRange / OptionsDescription
image_urls*Yesarraysample URI1–4Reference ordering matters.
prompt*Yesstring——Transformation + preservation clauses.
negative_promptNostring""≤500 charsAvoid list.
image_sizeNostringsquare_hdpresetsOutput framing.
num_imagesNointeger11–4Variations.
enable_prompt_expansionNobooleantrueon / offAuto expand prompts.
seedNointeger—0–2147483647Repeatability.

Pricing#

BillingRate
Per generated image$0.075

Total cost scales with num_images.


How to use#


  1. Curate references in the correct order before writing the prompt.
  2. Split instructions: “Change …” and “Keep … unchanged.”
  3. Run quick tests on the standard Wan 2.7 edit model, then promote winning prompts here for Pro output.
  4. Turn off enable_prompt_expansion when you need strict adherence to concise creative direction.
  5. Combine seed with small prompt changes for disciplined iteration.

Prompt tips#


  • For color transfer, describe both donor and target regions explicitly.
  • When editing typography or logos, add “do not warp letterforms.”
  • If textures look soft, request specific material descriptors (brushed metal, matte paint, and similar).

Related Wan 2.7 models#


  • Wan 2.7 Image Edit (standard) on RunComfy — cost-efficient iteration.
  • Wan 2.7 Pro Text-to-Image on RunComfy — text-only Pro stills.

Related Models

flux-3-image-klein/edit

Revise one to ten pictures from an instruction, at sizes up to 4K.

wan-2.7/edit

WAN 2.7 image edit: text-guided edits with 1–4 reference images, optional prompt expansion, bilingual instructions, and preset output sizes.

flux-3/image-edit

Edit up to ten images from a written instruction at 1K, 2K, or 4K.

Frequently Asked Questions

When should I use Wan 2.7 Pro image edit instead of standard Wan 2.7 image edit?

Use Wan 2.7 Pro image edit when you need higher fidelity than the standard Wan 2.7 image edit route—for example large print assets, tricky multi-reference work, or client delivery. Pro is priced at $0.075 per output image on RunComfy.

What is the Wan 2.7 Pro image edit price per image on RunComfy?

$0.075 per image. Multiply by num_images when you request several variations in one job.

Are the input fields the same for Wan 2.7 Pro image edit and standard Wan 2.7 image edit?

Yes. On RunComfy both playgrounds use image_urls, prompt, negative_prompt, image_size, num_images, enable_prompt_expansion, and seed. Output quality and price differ; the form matches so you can promote a tested prompt from standard to Pro.

Why choose Wan 2.7 Pro image edit over standard image edit?

Choose Pro when you need maximum detail retention—such as large-format print, complex color matching across references, or final delivery. Use standard edit for quicker, lower-cost exploration.

What is the maximum number of reference images for Wan 2.7 Pro image edit?

You must keep image_urls between one and four entries. Going outside that range can cause request errors.

How do I stop unwanted changes to faces or logos in Wan 2.7 Pro image edit?

Add explicit preservation lines (“do not alter the facial features”, “keep the logo sharp”), shorten the prompt when the model over-edits, and consider a fixed seed while you refine wording.

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 Wan 2.7 Pro Image Edit