AEmotionStudio commited on
Commit
0417404
·
verified ·
1 Parent(s): dd0705d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: apache-2.0
3
  base_model: zibojia/minimax-remover
4
  tags:
5
  - video
@@ -21,7 +21,6 @@ Key features:
21
  - **81-frame native batch size** — processes up to 81 frames at once for temporal consistency
22
  - **6–12 inference steps** — fast inference with iterative mask dilation
23
  - **Simplified DiT architecture** — lightweight compared to general-purpose video editors (~2.5 GB)
24
- - **Apache 2.0 license** — fully open source
25
 
26
  ## Files
27
 
@@ -66,9 +65,11 @@ When used with ComfyUI-FFMPEGA, MiniMax-Remover has the **highest priority** for
66
  3. **LaMa** (~200 MB VRAM) — always available fallback
67
  4. **Black fill** (0 VRAM) — FFmpeg fallback
68
 
69
- ## License
70
 
71
- Apache 2.0 see [LICENSE](https://github.com/zibojia/MiniMax-Remover/blob/main/LICENSE).
 
 
72
 
73
  ## Credits
74
 
 
1
  ---
2
+ license: cc-by-nc-4.0
3
  base_model: zibojia/minimax-remover
4
  tags:
5
  - video
 
21
  - **81-frame native batch size** — processes up to 81 frames at once for temporal consistency
22
  - **6–12 inference steps** — fast inference with iterative mask dilation
23
  - **Simplified DiT architecture** — lightweight compared to general-purpose video editors (~2.5 GB)
 
24
 
25
  ## Files
26
 
 
65
  3. **LaMa** (~200 MB VRAM) — always available fallback
66
  4. **Black fill** (0 VRAM) — FFmpeg fallback
67
 
68
+ ## ⚠️ License
69
 
70
+ > **Non-Commercial Use Only**: Model weights are licensed under **CC-BY-NC-4.0**. The source code is Apache 2.0.
71
+ >
72
+ > Users must accept the non-commercial license terms when downloading. Commercial use of the model weights requires separate licensing from the original authors.
73
 
74
  ## Credits
75