Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 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 |
-
|
|
|
|
|
|
|
| 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 |
|