MiniMax H3 ComfyUI: Setup Guide & Workflow Tips - Opensource

MiniMax H3 ComfyUI: Setup Guide & Workflow Tips

Learn how to run MiniMax H3 in ComfyUI for local AI video generation. Covers text-to-video, image-to-video, and reference-to-video workflows.

2026-08-10
MiniMax H3 Wiki Team
Quick Guide
  • MiniMax H3 in ComfyUI: Run open-weights AI video generation locally with full parameter control
  • Three core modes: Text-to-Video (T2V), Image-to-Video (I2V), and Reference-to-Video (R2V)
  • Native stereo audio: Dialogue, SFX, and music are generated together with the video
  • Hardware requirement: NVIDIA RTX 3060 or higher with sufficient system RAM
  • Speed optimization: Install Sage Attention to roughly double generation speed

MiniMax H3 ComfyUI Overview

MiniMax H3 brings powerful open-weights AI video generation directly to your local machine through ComfyUI. This integration allows creators to generate high-quality video content with native stereo audio, combining text prompts, reference images, and video clips into cohesive multimodal outputs. Running locally provides full control over every parameter without relying on cloud APIs.

Video Highlights:

  • Local text-to-video generation using the pruned int8 model on an RTX 3090
  • First and last frame image-to-video transitions with wipe and phase effects
  • Reference-to-video combining multiple images, video clips, and audio tracks
  • Voice cloning capabilities by merging character appearances and voices from separate clips
  • Pushing beyond the 15-second maximum duration limit successfully
Licensing Note

The MiniMax H3 license restricts downloads in the USA and European Union by default. However, individuals can request access by submitting a license request form. Approval emails are typically sent quickly. Always conduct your own research regarding your specific usage rights.

Core Generation Modes

MiniMax H3 operates through three primary generation workflows, each designed for different creative use cases. Understanding when to use each mode is essential for achieving optimal results.

Text-to-Video (T2V)

  • No input media required
  • Generates from text prompts only
  • Uses the FL2VA model
  • Best for rapid concept testing

Image-to-Video (I2V)

  • First and/or last frame control
  • Optional keyframe inputs
  • Uses the FL2VA model
  • Ideal for animating static images

Reference-to-Video (R2V)

  • Up to 9 images, 3 videos, 3 audio clips
  • Locks character identity and style
  • Uses the Ref2VA model
  • Best for consistent character work

Mode Comparison Table

FeatureText-to-VideoImage-to-VideoReference-to-Video
Model WeightsFL2VAFL2VARef2VA
Max Reference Images02 (first/last)9
Max Reference Videos003
Standalone Audio Inputs003
Native Audio OutputYesYesYes
Best Use CaseConcept explorationKeyframe animationCharacter consistency
Model Selection

T2V and I2V workflows share the same FL2VA model weights. R2V uses a separate Ref2VA diffusion model. When building custom workflows, use a boolean switch connected to your model loader groups to easily toggle between them.

Installation and Setup

Getting MiniMax H3 running in ComfyUI requires updating to a compatible version and downloading the appropriate model weights from Hugging Face.

1

Update ComfyUI

Update your ComfyUI installation to version 0.30.0 or later. Earlier versions lack native support for MiniMax H3 workflows and nodes.

2

Access Template Library

Navigate to Template Library > Video within the ComfyUI interface. Select any MiniMax H3 workflow that matches your intended generation mode.

3

Download Models

Follow the pop-up prompts to automatically download the required model files. Models are hosted on Hugging Face in the Comfy-Org/MiniMax-H3 repository.

4

Configure Resolution

Use the Resolution Selector node to set your output dimensions. Keep the multiple at 32 to match the H3 resolution grid. Choose from presets like 16:9, 9:16, or 1:1.

5

Run Generation

Connect your inputs, write your prompt, and execute the workflow. Generation time depends on your hardware, resolution, and number of references.

Hardware Recommendations

GPU TierMinimumRecommendedHigh-End
GPURTX 3060RTX 4070RTX 3090/4090
Model VersionPruned int8StandardStandard
Est. Gen Time (10s)8-12 min5-7 min3-5 min
Max Practical Res864x4801080p1216x672+
Model Variants

For users with 8GB VRAM cards like the RTX 3060, the pruned int8 model provides the best balance of quality and performance. Those with 24GB cards (RTX 3090/4090) can run full-precision models at higher resolutions without compromise.

Prompt Writing Strategies

Effective prompting in MiniMax H3 requires a structured approach that describes scenes, camera movements, and audio cues within a single prompt block. The model handles complex, multi-sentence prompts effectively.

Prompt Structure by Mode

ModePrompt StructureKey Syntax
T2VScene description, shot breakdown, camera moves, audio cuesPlain text
I2VMotion description, transition style, audio elementsPlain text
First/Last FrameDescribe transition from first to last image<Picture 0> and <Picture 1> tags
R2VAssign roles to each reference explicitly<Picture 1>, <Video 1>, <Audio 1> tags

Prompting Best Practices

  • Describe the whole scene first: State the location, character, and action before breaking into timed shots
  • Include audio instructions: Specify dialogue, sound effects, and music within the same prompt block
  • Use reference tags in R2V: Reference each input by tag in the exact connection order (e.g., <Picture 1>, <Video 1>)
  • Assign each reference a job: Explicitly state which reference drives identity, style, motion, camera, or voice
  • Leverage first/last frame tags: Even though the model auto-maps start and end frames, using <Picture 0> and <Picture 1> builds good habits for R2V workflows
Duration Control

The duration input snaps to the model's 17-frame-per-block (17k+5) grid at 24fps. While the stated maximum is 15 seconds, testing shows that pushing to 20 seconds can produce coherent results without garbled output.

Speed Optimization with Sage Attention

Generation speed is a critical factor when running large video models locally. Sage Attention provides a significant performance boost with minimal quality degradation.

1

Install SageAttention

Download the Python wheel matching your PyTorch and CUDA versions from the SageAttention releases page. Install using pip install <wheel-file>.

2

Install KJNodes

Use ComfyUI Manager to install the KJNodes custom nodes package. Alternatively, clone the repository into your ComfyUI/custom_nodes/ directory and restart ComfyUI.

3

Add the Patch Node

Insert a Patch Sage Attention KJ node between the UNETLoader and BasicGuider node. Set the sage_attention parameter to auto.

4

Run the Workflow

Execute your workflow as usual. Only the guider needs the patch; the scheduler remains unchanged.

Expected Console Messages

Sage Attention requires float16 or bfloat16 tensors. MiniMax H3 runs some layers in other dtypes, so you may see "Input tensors must be in dtype of torch.float16 or torch.bfloat16, using pytorch attention instead" messages. This is expected behavior and generation will still work correctly.

Optimization Comparison

SettingStandard AttentionSage AttentionGlobal Flag
SpeedBaseline~2x faster~2x faster
QualityFull fidelityMinimal lossMinimal loss
SetupNoneNode-based--use-sage-attention
Console WarningsNoneExpected fallback messagesExpected fallback messages

Workflow Architecture and Checklist

Understanding the node architecture helps you build and troubleshoot custom MiniMax H3 workflows. The workflow consists of model loaders, conditioning nodes, a standard K sampler, and output configuration.

Key Node Components

ComponentFunctionNotes
Model LoadersLoad FL2VA or Ref2VA weightsSeparate groups for first/last vs reference
CLIP and VAEText encoding and decodingShared across both model types
RG3 Fast Group BypassToggles active model groupEnsures only one group runs at a time
Resolution SelectorComputes width and heightOutputs connect to H3 node inputs
K SamplerStandard samplingNo special configuration needed
Video OutputRenders final MP4Supports GIF, frame interpolation
Expanding Inputs

While default workflows show a limited number of inputs, the system supports many more. You can easily expand to 5-6 images or add additional video and audio references by duplicating input nodes and updating your prompt tags accordingly.

MiniMax H3 ComfyUI Setup Checklist:

  • Update ComfyUI to version 0.30.0 or later
  • Download model weights from Hugging Face (Comfy-Org/MiniMax-H3)
  • Verify GPU has at least 8GB VRAM (RTX 3060+)
  • Ensure sufficient system RAM for model loading
  • Select appropriate model variant (pruned int8 for lower VRAM)
  • Set resolution multiple to 32 in Resolution Selector
  • Install Sage Attention and KJNodes for faster generation
  • Verify MiniMax H3 license terms for your region

FAQ

Q: What GPU do I need to run MiniMax H3 in ComfyUI?

An NVIDIA RTX 3060 with sufficient system RAM is the minimum requirement. For optimal performance, an RTX 3090 or 4090 is recommended, especially when working with multiple reference inputs at higher resolutions. The pruned int8 model variant works well on lower-VRAM cards.

Q: Can MiniMax H3 generate audio along with video?

Yes, MiniMax H3 generates native stereo audio including dialogue, sound effects, and music together with the video in a single MP4 file. You can also provide reference audio clips in R2V mode to clone voices or match specific audio styles.

Q: How many reference inputs can I use in Reference-to-Video mode?

R2V supports up to 9 reference images, 3 reference videos (each with its own soundtrack), and 3 standalone reference audio clips. You can mix and match these inputs to lock character identity, style, motion, camera moves, and voices.

Q: Is it possible to exceed the 15-second maximum video duration?

While the official maximum is 15 seconds, testing shows that setting the length to 20 seconds can still produce coherent results. The duration input snaps to the model's 17-frame-per-block grid at 24fps, so durations follow a specific increment pattern.

Q: How do I switch between Text-to-Video and Reference-to-Video in one workflow?

Use an RG3 Fast Group Bypass node to ensure only one model loader group is active at a time. A boolean switch based on the label set in the model loader groups lets you toggle between FL2VA and Ref2VA conditioning and latents easily.