README: 3-second samples of the five test prompts at 480p and 768p with generation times
577de1e verified | license: other | |
| license_name: minimax-h3-community-license-agreement | |
| license_link: LICENSE | |
| base_model: | |
| - Comfy-Org/MiniMax-H3 | |
| - TaoLiveAIGC/TaoMate-H3 | |
| - Asirus/TaoMate_H3_3_Step_LoRA | |
| tags: | |
| - comfyui | |
| - video-generation | |
| - text-to-video | |
| - image-to-video | |
| - minimax-h3 | |
| - int8 | |
| # MiniMax H3 Experimental | |
| Experimental MiniMax H3 files for ComfyUI. | |
| ## minimax_h3_fl2va_pruned_int8_convrot_taomax3.safetensors | |
| MiniMax H3 FL2VA (pruned, int8 ConvRot) with the **TaoMate H3 3-step MAXQUALITY** step-distillation LoRA merged into the | |
| weights. It renders a video with sound in **3 sampling steps** instead of 20, with no LoRA node, and keeps ComfyUI's | |
| fast int8 path at every resolution. When the model is streamed from RAM (large sizes on 24 GB cards), a LoRA loaded at run | |
| time makes every patched int8 layer run in bf16; a merged file avoids that. | |
| **This is a modified file.** Made from Comfy-Org's | |
| [`minimax_h3_fl2va_pruned_int8_convrot.safetensors`](https://huggingface.co/Comfy-Org/MiniMax-H3) and | |
| [`taomate_h3_3step_MAXQUALITY_bf16.safetensors`](https://huggingface.co/Asirus/TaoMate_H3_3_Step_LoRA) (the official | |
| TaoMate-H3 3-step LoRA from Alibaba's TaoLive AIGC team, converted for ComfyUI by Asirus) at strength 1.0 by ComfyUI's own LoRA merge: each patched int8 ConvRot linear (attention and MLP of the 50 | |
| blocks, and the token refiner) was dequantized, had the LoRA added, and was requantized. Every tensor the LoRA does not | |
| touch is byte-identical to the official file, in its original dtype. Same 932 tensors, same layout and size (21.0 GB) as the | |
| official file. | |
| ### Running it | |
| Stock ComfyUI with MiniMax H3 support loads it like the official int8 file: put it in `ComfyUI/models/diffusion_models/` | |
| and pick it in **Load Diffusion Model** (weight dtype `default`). Use the rest of the official MiniMax H3 setup | |
| (text encoder `qwen3vl_32b_minimax_h3_nvfp4_awq` or `qwen3vl_32b_minimax_h3_int8_convrot`, VAE | |
| `minimax_h3_video_vae_int8_convrot`, all from [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)). As | |
| with the official int8 files, PyTorch built for CUDA 13.0 or newer is recommended. | |
| Sampling (do not add the TaoMate LoRA again; it is already inside): | |
| | Setting | Value | | |
| |---|---| | |
| | Sampler | `res_multistep` (KSamplerSelect) | | |
| | Sigmas | `1.0, 0.9601, 0.8575, 0` (ManualSigmas), i.e. 3 steps | | |
| | Guider | BasicGuider (no CFG) | | |
| | Sampler node | SamplerCustomAdvanced | | |
| The LoRA's own card also suggests `euler` or `er_sde`, the | |
| `simple` scheduler, 3 steps and a video shift of 8-12 (audio 3); those settings apply to this file the same way. | |
| ### Samples | |
| The first 3 seconds of each test render (5.2 s were generated), with sound. Five hard text-to-video prompts (`samples/prompts.py`), seed 42, 3 steps with the settings above, RTX 4090 at locked clocks (2235 MHz core), ComfyUI with SageAttention. Times are for the whole 124-frame clip: the sampler, then the total including decoding and saving (the text encoding was cached). For scale, stock MiniMax H3 int8 at 20 steps takes about 51 s (480p) and 184 s (768p) for the sampler on the same card. Full-length videos and frame sheets are in `samples/`. | |
| #### Market dialogue | |
| Two faces, alternating lip sync, two voices. Good at both sizes: both faces stable, the tomato and gestures follow the text. | |
| | 864脳480 | 1344脳768 | | |
| |---|---| | |
| | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/dialogue_480p_3s.mp4" controls width="100%"></video><br>sampler 8.7 s 路 total 16.1 s | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/dialogue_768p_3s.mp4" controls width="100%"></video><br>sampler 26.3 s 路 total 35.2 s | | |
| #### Pianist | |
| Fast hands on the keys, music in sync. Hands hold together; a blurred extra hand at the left edge at 480p; the tilt to his face works. | |
| | 864脳480 | 1344脳768 | | |
| |---|---| | |
| | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/pianist_480p_3s.mp4" controls width="100%"></video><br>sampler 8.7 s 路 total 16.1 s | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/pianist_768p_3s.mp4" controls width="100%"></video><br>sampler 27.5 s 路 total 38.9 s | | |
| #### Dog and lake | |
| Splash, wet fur, fast animal motion. The weakest: the dog never visibly leaps; it sits in a splash at the end of the dock. | |
| | 864脳480 | 1344脳768 | | |
| |---|---| | |
| | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/dog_splash_480p_3s.mp4" controls width="100%"></video><br>sampler 8.7 s 路 total 16.3 s | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/dog_splash_768p_3s.mp4" controls width="100%"></video><br>sampler 27.6 s 路 total 39.0 s | | |
| #### Neon sign in rain | |
| Readable text, rain, reflections, a camera move. "OPEN ALL NIGHT" reads cleanly at 480p; at 768p the sign moves to the window and NIGHT is garbled. Quiet soundtrack. | |
| | 864脳480 | 1344脳768 | | |
| |---|---| | |
| | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/neon_rain_480p_3s.mp4" controls width="100%"></video><br>sampler 8.7 s 路 total 16.4 s | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/neon_rain_768p_3s.mp4" controls width="100%"></video><br>sampler 27.5 s 路 total 39.0 s | | |
| #### Skateboard trick | |
| Full-body motion, handheld camera, a crowd. Coherent rider and cheering friends; the kickflip is only clear at 768p. | |
| | 864脳480 | 1344脳768 | | |
| |---|---| | |
| | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/skate_480p_3s.mp4" controls width="100%"></video><br>sampler 8.7 s 路 total 16.4 s | <video src="https://huggingface.co/PedroMarinhoDev/MiniMax-H3-Experimental/resolve/main/samples/clips/skate_768p_3s.mp4" controls width="100%"></video><br>sampler 27.5 s 路 total 39.2 s | | |
| ### License and use restrictions | |
| MiniMax H3 and this file are licensed under the **MiniMax H3 Community License Agreement** (see `LICENSE` and `NOTICE`). | |
| By downloading or using this file you agree to that agreement, including its Acceptable Use Policy (Exhibit A), its use | |
| restrictions (Section V) and its territorial terms: the license does not cover the European Union, the United Kingdom, | |
| the Republic of Korea or the United States of America. The TaoMate LoRA is published under the same license. | |
| MiniMax H3 is licensed under the MiniMax H3 Community License Agreement, Copyright 漏 2026 MiniMax. All Rights Reserved. | |
| Credits: [MiniMax](https://huggingface.co/MiniMaxAI/MiniMax-H3) (MiniMax H3), [TaoLive AIGC](https://huggingface.co/TaoLiveAIGC/TaoMate-H3) | |
| (TaoMate), [Asirus](https://huggingface.co/Asirus/TaoMate_H3_3_Step_LoRA) (ComfyUI conversion of the LoRA), | |
| [Comfy-Org](https://huggingface.co/Comfy-Org/MiniMax-H3) (int8 ConvRot repack). | |