# minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors

> Veda sparse-attention predictor for MiniMax H3 · Up to 3.1× faster MiniMax H3 sampling

This is the Veda predictor for MiniMax H3. It learns which 10% of attention matters and lets the model skip the rest, for up to 3.1× faster end-to-end generation. Put it in ComfyUI/models/veda and select it in the Veda Sparse Attention node. If you searched for h3_t2va_deda_8nfe_600step_preview_fp8, this is the file.

There is no file named h3_t2va_deda…; “deda” is a common misspelling of Veda. The real filename starts with minimax_h3_t2va_veda.

## Facts

- **Type:** Sparse-attention predictor
- **Format:** Safetensors · fp8
- **Size:** 275 MB (275,415,648 bytes)
- **SHA256:** 2a8d8845c5342756a2781e8e69563940e4bb573c9a40ebb534915ff8fd76573a
- **ComfyUI folder:** ComfyUI/models/veda/
- **Loader node:** Veda Sparse Attention (MiniMax H3)
- **License:** MiniMax H3 Community License

## What is minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors?

Attention is most of the cost of video diffusion, but only a small share of it changes the result. Veda trains a light predictor, distilled from the full model, to pick the most important 10% of attention so H3 can skip the rest. The authors report up to 6.8× faster attention and 3.1× faster end to end, with quality on par with full attention.

It is not a LoRA: model weights and style stay the same, so it combines with any LoRA or fine-tuned H3. “T2VA” and “8NFE 600step” describe how this preview checkpoint was trained, not where it can be used.

Searches for h3_t2va_deda_8nfe_600step_preview_fp8.safetensors land here because no file by that name exists; it is a misspelling of this one.

## Download and install

- [Hugging Face · Veda-Sparse](https://huggingface.co/Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview/resolve/main/minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors) · saves as `minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors` · Official release. Recommended.

```sh
cd ComfyUI/models/veda
wget -O minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors \
  https://huggingface.co/Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview/resolve/main/minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors
sha256sum minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors
# 2a8d8845c5342756a2781e8e69563940e4bb573c9a40ebb534915ff8fd76573a
```

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.

## How to load it in ComfyUI

Veda patches how MiniMax H3 computes attention. The Veda Sparse Attention node reads the predictor from models/veda and goes between the model loader and the sampler.

- **Works beyond T2VA:** The authors say this predictor also works for FL2VA and Ref2VA, at any step count.
- **Pair with Turbo:** It was trained with the Turbo LoRA for 8-step generation, where the speedup is largest.

## Files a MiniMax H3 video workflow needs

Use the Ref2VA diffusion model instead of FL2VA for reference-to-video workflows.

- [`minimax_h3_fl2va_pruned_int8_convrot.safetensors`](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors) · Diffusion model (FL2VA) · `models/diffusion_models/` · 20.97 GB
- [`qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors`](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors) · Text encoder (Qwen3-VL 32B) · `models/text_encoders/` · 15.69 GB
- [`minimax_h3_video_vae_fp16.safetensors`](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors) · Video VAE · `models/vae/` · 5.21 GB
- [`minimax_h3_audio_vae_fp32.safetensors`](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors) · Audio VAE · `models/vae/` · 605 MB
- [`minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors`](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/loras/minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors) · Turbo LoRA, 4 steps · `models/loras/` · 1.96 GB

## Workflows: Uses other MiniMax H3 models

These workflows load another MiniMax H3 model. Select minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors in their Veda Sparse Attention (MiniMax H3) node to use it instead.

- [MiniMax H3 Veda Acceleration | 3x Fast Ref-to-Video](https://www.runcomfy.com/comfyui-workflows/minimax-h3-veda-acceleration)

## Same file, other names, and alternatives

- `minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors` · This page · T2VA preview predictor · 275 MB · All H3 modes
- `minimax_h3_r2va_veda_preview_fp8.safetensors` · Sibling · trained on Ref2VA · — · Reference-to-video quality

## Common errors and fixes

### Value not in list: model: 'minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/veda. Usually the file is missing, sits in a different folder, or was saved under another name such as h3_t2va_deda_8nfe_600step_preview_fp8.safetensors.

Fix: Move the file into ComfyUI/models/veda/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

### Missing node type: VedaSparseAttention

Why: Veda Sparse Attention (MiniMax H3) is not built into ComfyUI. It comes from the Veda-on-ComfyUI custom node pack.

Fix: Install Veda-on-ComfyUI with ComfyUI Manager (or git clone it into ComfyUI/custom_nodes), then restart ComfyUI.

### SafetensorError: Error while deserializing header

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 275,415,648 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · Veda-Sparse if not.

## FAQ

### Is h3_t2va_deda_8nfe_600step_preview_fp8.safetensors a real file?

No. It is a misspelling of `minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors`, the Veda predictor on this page.

### Which folder: veda or veda_scorers?

The official Veda-on-ComfyUI node reads `models/veda`. The T8 node pack uses `models/veda_scorers` instead. Put the file where your node looks.

### Where do I put minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors in ComfyUI?

In `ComfyUI/models/veda/`. Then refresh the node list or restart ComfyUI so Veda Sparse Attention (MiniMax H3) lists the file.

### Which ComfyUI node loads minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors?

[Veda Sparse Attention (MiniMax H3)](/comfyui-nodes/Veda-on-ComfyUI/veda-sparse-attention). It comes from the [Veda-on-ComfyUI](https://github.com/veda-sparse/Veda-on-ComfyUI) custom node pack, so install that first.

### Can I use minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors commercially?

Yes, within the MiniMax H3 Community License. Commercial products must show “MiniMax H3” in their interface, and companies with more than US$20 million in yearly revenue need written permission from MiniMax first. The license also limits use to its listed territories, so read it before shipping.

## Sources

- [Veda-Sparse on Hugging Face](https://huggingface.co/Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview)
- [Veda-on-ComfyUI](https://github.com/veda-sparse/Veda-on-ComfyUI)
- [Veda paper (arXiv 2605.30325)](https://arxiv.org/abs/2605.30325)

Canonical page: https://www.runcomfy.com/comfyui-workflows/model-files/minimax_h3_t2va_veda_8nfe_600step_preview_fp8.safetensors
