Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,74 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- APRIL-AIGC/UltraVideo
|
| 5 |
+
base_model:
|
| 6 |
+
- Wan-AI/Wan2.1-T2V-1.3B
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# UltraWan LoRA — ComfyUI Conversion (Unofficial)
|
| 10 |
+
|
| 11 |
+
This repository contains **converted LoRA weights** from the official [**APRIL-AIGC/UltraWan**](https://huggingface.co/APRIL-AIGC/UltraWan) release.
|
| 12 |
+
The only modification made was converting the `.bin` / original format into `.safetensors` compatible with **ComfyUI**.
|
| 13 |
+
No training, fine-tuning, or architecture changes were performed.
|
| 14 |
+
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
## 📌 What This Is
|
| 18 |
+
|
| 19 |
+
- ✅ Direct conversion of original UltraWan LoRA weights to **ComfyUI-compatible safetensors format**
|
| 20 |
+
- ❌ Not trained, modified, or altered in any way beyond the format change
|
| 21 |
+
- 🎯 For users who want to test **UltraWan LoRA** with ComfyUI’s Text-to-Video pipelines
|
| 22 |
+
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
## 🔗 Attribution
|
| 26 |
+
|
| 27 |
+
- **Original Model**: [**APRIL-AIGC/UltraWan**](https://huggingface.co/APRIL-AIGC/UltraWan)
|
| 28 |
+
- **Base Model Architecture**: [TencentARC/Wan](https://github.com/TencentARC/Wan)
|
| 29 |
+
- **License**: CC-BY-4.0 with Additional Restrictions (see below)
|
| 30 |
+
|
| 31 |
+
> I do **not** claim ownership of the original model, dataset, or LoRA weights.
|
| 32 |
+
> All credit goes to the **APRIL-AIGC** team and the authors of the [UltraVideo Dataset](https://arxiv.org/abs/2506.13691).
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
## 📄 License & Use
|
| 37 |
+
|
| 38 |
+
These weights are subject to the license terms of the **UltraVideo Dataset**, which include:
|
| 39 |
+
|
| 40 |
+
- ❗ **Non-commercial research only**
|
| 41 |
+
- ⚠️ No redistribution of raw videos or identifiable content
|
| 42 |
+
- ✅ You may use these weights to run inference in ComfyUI for research/academic purposes
|
| 43 |
+
- ❌ You may **not** use these weights or outputs for commercial purposes, product development, or monetization
|
| 44 |
+
|
| 45 |
+
Please see the full license in [`LICENSE`](./LICENSE).
|
| 46 |
+
|
| 47 |
+
---
|
| 48 |
+
|
| 49 |
+
## 📂 Contents
|
| 50 |
+
|
| 51 |
+
| File | Description |
|
| 52 |
+
|------|-------------|
|
| 53 |
+
| `lora_ultrawan_4k.safetensors` | LoRA converted to safetensors, ready for ComfyUI |
|
| 54 |
+
| `LICENSE` | UltraVideo Dataset License (CC-BY-4.0 + Restrictions) |
|
| 55 |
+
| `README.md` | This file |
|
| 56 |
+
|
| 57 |
+
---
|
| 58 |
+
|
| 59 |
+
## 🧩 How to Use in ComfyUI
|
| 60 |
+
|
| 61 |
+
Place the `.safetensors` file in:
|
| 62 |
+
|
| 63 |
+
```
|
| 64 |
+
ComfyUI/models/loras/
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
Then use a **LoRA Loader** node in your workflow and select the LoRA file from the dropdown menu.
|
| 68 |
+
|
| 69 |
+
---
|
| 70 |
+
|
| 71 |
+
*This is a community-contributed format conversion. All rights belong to the original creators.*
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
|