Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,9 @@ base_model:
|
|
| 13 |
|
| 14 |
Repackaged model files for ComfyUI.
|
| 15 |
|
| 16 |
-
Original model repository:
|
|
|
|
|
|
|
| 17 |
|
| 18 |
The Qwen3-VL-32B `nvfp4_awq` quant is converted from: https://huggingface.co/cybermotaz/Qwen3-VL-32B-Instruct-NVFP4
|
| 19 |
|
|
@@ -45,6 +47,10 @@ Place the files in the following folders:
|
|
| 45 |
│ │ ├── qwen3vl_32b_minimax_h3_bf16.safetensors
|
| 46 |
│ │ ├── qwen3vl_32b_minimax_h3_int8_convrot.safetensors
|
| 47 |
│ │ └── qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
│ ├── 📂 vae/
|
| 49 |
│ │ ├── minimax_h3_audio_vae_fp32.safetensors
|
| 50 |
│ │ └── minimax_h3_video_vae_fp16.safetensors
|
|
|
|
| 13 |
|
| 14 |
Repackaged model files for ComfyUI.
|
| 15 |
|
| 16 |
+
Original model repository:
|
| 17 |
+
- https://huggingface.co/MiniMaxAI/MiniMax-H3
|
| 18 |
+
- https://huggingface.co/lightx2v/Minimax-h3-Turbo
|
| 19 |
|
| 20 |
The Qwen3-VL-32B `nvfp4_awq` quant is converted from: https://huggingface.co/cybermotaz/Qwen3-VL-32B-Instruct-NVFP4
|
| 21 |
|
|
|
|
| 47 |
│ │ ├── qwen3vl_32b_minimax_h3_bf16.safetensors
|
| 48 |
│ │ ├── qwen3vl_32b_minimax_h3_int8_convrot.safetensors
|
| 49 |
│ │ └── qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
|
| 50 |
+
│ ├── 📂 loras/
|
| 51 |
+
│ │ ├── minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors
|
| 52 |
+
│ │ ├── minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors
|
| 53 |
+
│ │ └── minimax_h3_ref2v_turbo_4step_v0.1_comfyui_bf16.safetensors
|
| 54 |
│ ├── 📂 vae/
|
| 55 |
│ │ ├── minimax_h3_audio_vae_fp32.safetensors
|
| 56 |
│ │ └── minimax_h3_video_vae_fp16.safetensors
|