MiniMax H3 Taomate 3-Step Acceleration | Image to Video
Load Diffusion Model
Already loads minimax_h3_ref2va_pruned_fp8_scaled.safetensors
ComfyUI model file · Diffusion model (video + audio)
MiniMax H3 Ref2VA pruned (fp8 scaled) · Reference-to-video diffusion model for MiniMax H3
This is MiniMax H3’s Ref2VA model, pruned and stored in fp8 scaled. It makes video with sound from your prompt plus reference images of characters, objects or places. Put it in ComfyUI/models/diffusion_models and load it with Load Diffusion Model.
Civitai names this download minimaxH3PrunedFp8_ref2vaPrunedFp8.safetensors. Same bytes. Comfy-Org suggests int8_convrot instead when your PyTorch supports it.
minimax_h3_ref2va_pruned_fp8_scaled.safetensors
The short version
MiniMax H3 ships as two diffusion models: FL2VA for text, image and first-last-frame to video, and Ref2VA for reference-guided video. This file is the Ref2VA one. You give it up to several reference images and a prompt, and it keeps those characters or objects consistent through the clip while generating matching audio.
“Pruned” means Comfy-Org removed weights the model does not need at inference, which drops the full model from 66 GB to 40 GB in bf16. “fp8 scaled” halves it again to 20.96 GB. Comfy-Org recommends this fp8 file only if you cannot use the int8_convrot version.
Civitai’s listing of the same file (model 2832970) renames it minimaxH3PrunedFp8_ref2vaPrunedFp8.safetensors on download. The Civitai API hash matches the Hugging Face file.
Install
ComfyUI repackage of the official weights. Recommended.
saves as minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Same bytes under Civitai’s download name. May ask you to sign in.
saves as minimaxH3PrunedFp8_ref2vaPrunedFp8.safetensors
ComfyUI/ └─ models/ ├─ … └─ diffusion_models/ └─ minimax_h3_ref2va_pruned_fp8_scaled.safetensors
$ cd ComfyUI/models/diffusion_models$ wget -O minimax_h3_ref2va_pruned_fp8_scaled.safetensors \$ https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_pruned_fp8_scaled.safetensors$ sha256sum minimax_h3_ref2va_pruned_fp8_scaled.safetensors# f86f2f79ebd2d76eb8eeb46091e83982e6ff51d255747e7b16e92834b392b8e9
Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.
Use
Load Diffusion Model reads the diffusion model and outputs a MODEL for the sampler. The text encoder and VAE load in their own nodes.
Works with
minimax_h3_ref2va_pruned_fp8_scaled.safetensors is one part of the stack. A workflow that reports a missing model usually needs these too. Use the Ref2VA diffusion model instead of FL2VA for reference-to-video workflows.
| File | Role | Folder | Size | Download |
|---|---|---|---|---|
| qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors | Text encoder (Qwen3-VL 32B) | models/text_encoders/ | 15.69 GB | Get |
| minimax_h3_video_vae_fp16.safetensors | Video VAE | models/vae/ | 5.21 GB | Get |
| minimax_h3_audio_vae_fp32.safetensors | Audio VAE | models/vae/ | 605 MB | Get |
| minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors | Turbo LoRA, 4 steps(optional) | models/loras/ | 1.96 GB | Get |
Run it
We match workflows by the model files they load: this exact file first, then other versions of it, then workflows built for the same use, then other models from the same family.
1 workflow
These workflows already load minimax_h3_ref2va_pruned_fp8_scaled.safetensors. Open one and run it as is.
Load Diffusion Model
Already loads minimax_h3_ref2va_pruned_fp8_scaled.safetensors
19 workflows
These workflows load a different precision or format of the same model. Select minimax_h3_ref2va_pruned_fp8_scaled.safetensors in their Load Diffusion Model node to use this version.
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
MiniMax_H3_Ref2VA_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_pruned_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
6 workflows
These workflows load another reference-to-video model in the same folder, or they are reference-to-video workflows that already have a Load Diffusion Model node. Select minimax_h3_ref2va_pruned_fp8_scaled.safetensors there.
Load Diffusion Model
Minimax-h3_Singularity_ref2va_v2_int8.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
Minimax-h3_Singularity_ref2va_v1.3_int8.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
Minimax-h3_Singularity_ref2va_v1.3_int8.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
Minimax-h3_Singularity_ref2va_v1.3_int8.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
Minimax-h3_Singularity_ref2va_v1.3_int8.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Load Diffusion Model
minimax_h3_ref2va_int8_convrot.safetensors
Replace with minimax_h3_ref2va_pruned_fp8_scaled.safetensors
Compare
| File | Relation | Size | Best for |
|---|---|---|---|
| minimax_h3_ref2va_pruned_fp8_scaled.safetensors | This page · pruned fp8 scaled | 20.96 GB | GPUs without int8_convrot support |
| minimax_h3_ref2va_pruned_int8_convrot.safetensors | Same model · int8 convrot | 20.97 GB | Preferred by Comfy-Org on PyTorch cu130 |
| minimax_h3_ref2va_pruned_w6a8.safetensors | Same model · w6a8 | 15.98 GB | Less VRAM |
| minimax_h3_ref2va_pruned_bf16.safetensors | Same model · bf16 | 40.23 GB | Highest fidelity, large GPUs |
| minimax_h3_fl2va_pruned_int8_convrot.safetensors | Sibling model · FL2VA | 20.97 GB | Text, image and first-last-frame to video |
Troubleshoot
Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/diffusion_models. Usually the file is missing, sits in a different folder, or was saved under another name such as minimaxH3PrunedFp8_ref2vaPrunedFp8.safetensors.
Fix: Move the file into ComfyUI/models/diffusion_models/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.
Why: The model alone is 21 GB, before the text encoder, VAEs and activations for long clips.
Fix: Lower the resolution or clip length, enable model offloading, or switch to the w6a8 file. A 48 GB or larger cloud GPU runs it at full settings.
Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.
Fix: Check that the file is exactly 20,958,205,608 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · Comfy-Org/MiniMax-H3 if not.
Rather skip the setup?
Run MiniMax H3 Taomate 3-Step Acceleration in your browser on a cloud GPU. Nothing to download.
FAQ
f86f2f79ebd2d76eb8eeb46091e83982e6ff51d255747e7b16e92834b392b8e9 is the same on both sites.ComfyUI/models/diffusion_models/. Then refresh the node list or restart ComfyUI so Load Diffusion Model lists the file.Sources: Comfy-Org/MiniMax-H3 on Hugging Face · MiniMaxAI/MiniMax-H3 (original weights) · ComfyUI MiniMax H3 tutorial · Civitai model 2832970
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.