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

MiniMax H3 Image Edit: Multi-Image Editing up to 4K on Models and API | RunComfy

minimax/minimax-h3-image/edit
Say what should change. Refer to uploads in order as Picture 1, Picture 2, and so on. Up to 5000 characters.
Image 1
1 to 16 reference images. Each file up to 20 MB. Each image adds $0.007.
auto follows the first reference image, limited to 1:3 through 3:1.
1K and 2K are $0.029 per output image. 4K is $0.085. Reference images are extra.
Rewrite the instruction into a fuller English description before the edit.
PNG is the default. JPEG is smaller.
Use -1 for a new result. A fixed seed repeats only when Expand Prompt is off.
Idle
Output image: $0.029 at 1K or 2K, $0.085 at 4K. Each reference image adds $0.007, including the first. One 2K edit with one reference is $0.036.

Parameters#


ParameterRequiredTypeDefaultRange / OptionsDescription
prompt*Yes (*)stringExample lineUp to 5000 charactersWhat MiniMax H3 Image Edit should change. Call uploads Picture 1, Picture 2, in order.
image_urls*Yes (*)arrayExample still1-16 images, each under 20 MBReference pictures. Each one adds $0.007.
aspect_ratioNostringautoauto, 1:1, 5:4, 4:5, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9auto follows the first picture, within 1:3 to 3:1.
resolutionNostring2K1K, 2K, 4KOutput tier for MiniMax H3 Image Edit.
expand_promptNobooleantruetrue, falseRewrite the instruction before the edit.
output_formatNostringpngpng, jpegFile type.
seedNointeger-1-1 to 2147483647Repeats only when expansion is off.

Pricing#


MiniMax H3 Image Edit bills the output image, then adds a fee for every reference image, including the first.


ResolutionOutput imageEach reference image
1K$0.029$0.007
2K$0.029$0.007
4K$0.085$0.007

One 2K edit with one reference is $0.036. Aspect ratio, prompt expansion, seed, and file type do not add a fee.


Frequently Asked Questions

What is MiniMax H3 Image Edit used for?

MiniMax H3 Image Edit changes or combines 1 to 16 reference images into one still at 1K, 2K, or 4K. Name each upload in order as Picture 1, Picture 2, and so on. Product and campaign teams use MiniMax H3 Image Edit when the source pictures already exist.

How should I write a prompt for MiniMax H3 Image Edit?

Say what must change and what must stay. Refer to files by their upload order. MiniMax H3 Image Edit follows Picture 1 as the first image in the list, not as a name you invent.

What input limits apply to MiniMax H3 Image Edit?

You can send 1 to 16 images. Each file should be under 20 MB. The prompt can be up to 5000 characters. MiniMax H3 Image Edit uses auto to follow the first image, within a 1:3 to 3:1 frame.

Does MiniMax H3 Image Edit support a negative prompt or extra steps?

No. Sampling stays at six steps, and there is no negative field. Change the instruction or swap a reference instead. MiniMax H3 Image Edit will not take a step count.

When does a seed repeat on MiniMax H3 Image Edit?

Only when Expand Prompt is off and the same references are sent in the same order. With expansion on, the rewritten instruction changes. MiniMax H3 Image Edit will not match a previous file if either of those moves.

How is MiniMax H3 Image Edit different from the text-to-image page?

The text page does not take pictures. MiniMax H3 Image Edit requires at least one reference and charges for every reference, including the first. Use the text page when you are starting from words alone.

Can developers call MiniMax H3 Image Edit from the RunComfy API?

Yes. Confirm the references and the instruction in the RunComfy model UI, then send the same image URLs and settings to the RunComfy API. MiniMax H3 Image Edit returns one image per request.

How much does MiniMax H3 Image Edit cost on RunComfy?

The output image is $0.029 at 1K or 2K, and $0.085 at 4K. Each reference image adds $0.007, including the first. One 2K edit with one reference is $0.036 on MiniMax H3 Image Edit.

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.