lym00 commited on
Commit
3d9f50f
·
verified ·
1 Parent(s): 63d92aa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -3
README.md CHANGED
@@ -6,14 +6,20 @@ license: apache-2.0
6
  > ⚠️ **Notice**
7
  > This project is intended for **experimental use only**.
8
 
 
9
 
10
- This is an addon experiment using **VACE scopes** extracted from **[Wan2.1 VACE T2V 14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B)** and injected into the **[Wan2.2 T2V A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B)**.
11
 
12
- Tested with **2-step High Noise + 2-step Low Noise** sampling with the [LightX2V LoRA](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v), it's working fine in ComfyUI.
 
 
 
 
 
13
 
14
  There's news where VACE team might have a **fix for the [color shifting](https://github.com/ali-vilab/VACE/issues/44) issue** to be released.
15
 
16
- Will be waiting for the official fix before testing further.
17
 
18
  ---
19
 
 
6
  > ⚠️ **Notice**
7
  > This project is intended for **experimental use only**.
8
 
9
+ This is an addon experiment of **[Wan2.2 T2V A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B)** and VACE scopes from **[Wan2.1 VACE T2V 14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B)**.
10
 
11
+ The process involved injecting VACE scopes into the target models, using scripts provided by [wsbagnsv1](https://huggingface.co/wsbagnsv1).
12
 
13
+ All quantized versions were created from the FP16 model using the conversion scripts provided by city96, available at the ComfyUI-GGUF GitHub repository.
14
+
15
+
16
+ ## Notes
17
+
18
+ Tested with **2-step High Noise** and **2-step Low Noise** sampling with the [LightX2V LoRA](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v), it's working fine in ComfyUI.
19
 
20
  There's news where VACE team might have a **fix for the [color shifting](https://github.com/ali-vilab/VACE/issues/44) issue** to be released.
21
 
22
+ Will be waiting for the official fix before testing further.
23
 
24
  ---
25