| --- |
| license: other |
| license_name: minimax-h3-community-license-agreement |
| license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE |
| tags: |
| - comfyui |
| - nvfp4 |
| - quantized |
| - video |
| - text-to-video |
| - minimax-h3 |
| base_model: Comfy-Org/MiniMax-H3 |
| base_model_relation: quantized |
| --- |
| |
| # MiniMax-H3 T2V (FL2VA) — NVFP4 |
|
|
| NVFP4 quantization of the **MiniMax-H3 FL2VA/t2va** diffusion transformer for ComfyUI. |
| This is the **text-to-video** variant (prompt → video, with optional first/last-frame |
| conditioning) — the first NVFP4 T2V release of MiniMax-H3 (existing NVFP4 releases |
| covered only Ref2VA). |
|
|
| - Original model: https://huggingface.co/MiniMaxAI/MiniMax-H3 |
| - ComfyUI repackage (bf16 source): https://huggingface.co/Comfy-Org/MiniMax-H3 |
|
|
| ## File |
|
|
| | file | size | notes | |
| |---|---|---| |
| | `diffusion_models/minimax_h3_fl2va_nvfp4_mixed.safetensors` | 24.4 GB | attn/mlp → NVFP4, adaln → FP8 (recommended) | |
|
|
| ## Requirements |
|
|
| - **NVIDIA Blackwell GPU** (RTX 50-series, RTX PRO 6000, DGX Spark / GB10). On older |
| GPUs the NVFP4 path is emulated — use Comfy-Org's `int8_convrot` files instead. |
| - **ComfyUI ≥ 0.30.0** with native MiniMax-H3 support (`comfy_extras/nodes_minimax_h3.py`). |
|
|
| ## Usage |
|
|
| 1. Place the file in `ComfyUI/models/diffusion_models/` |
| 2. Load the `video_minimax_h3_r2v.json` workflow (or use `MiniMaxH3ImageToVideo` with no keyframes for pure T2V) |
| 3. Suggested params: `res_multistep` sampler, frame length `17n + 5` (e.g. 22, 39, 56, 73), 20 steps, 864×480 test resolution |
|
|
| ## Quantization profile (mixed) |
|
|
| - 200 attn/mlp layers → NVFP4 (Tensor Core) |
| - 50 adaln layers → FP8 (E4M3FN) — modulation path kept higher precision |
| - norms, biases, embedders, heads → BF16 |
| - Converted with `comfy-kitchen` (`TensorCoreNVFP4Layout`) — per-layer `.comfy_quant` metadata, loadable natively by ComfyUI. |
|
|
| ## Companion files |
|
|
| Also needed (from `Comfy-Org/MiniMax-H3`): |
| - `text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors` (15.7 GB) |
| - `vae/minimax_h3_video_vae_fp16.safetensors` (5.2 GB) |
| - `vae/minimax_h3_audio_vae_fp32.safetensors` (0.6 GB) |
|
|
| ## Bonus: uncensored ("Heretic") text encoder — NVFP4 |
|
|
| Optional drop-in replacement for the standard MiniMax-H3 text encoder. Built from |
| `ethanfel/Qwen3-VL-32B-Ultra-Heretic-MiniMax-H3-ComfyUI-INT8-ConvRot` (itself derived from |
| `llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic`, abliterated with ARA edits on |
| `attn.o_proj` layers 31-40), then converted to NVFP4 with the same `.comfy_quant` format. |
|
|
| | file | size | notes | |
| |---|---|---| |
| | `text_encoders/qwen3vl_32b_minimax_h3_ultra_uncensored_heretic_nvfp4.safetensors` | 16.5 GB | language layers 0-49 + vision tower, 350 layers NVFP4, rest BF16 | |
|
|
| Usage: select it in `CLIPLoader` with type `minimax` (same as the standard encoder). |
| Source's INT8-only generation-tail (layers 50-63) is not included; the conditioning |
| path is identical to the standard MiniMax-H3 CLIP. |
|
|
| Abliteration reduces refusal behavior — test content for quality/appropriateness. |
|
|
|
|
