mirror of
https://www.modelscope.cn/Kijai/WanVideo_comfy_fp8_scaled.git
synced 2026-04-02 05:52:54 +08:00
Upload folder using ModelScope SDK
This commit is contained in:
3
I2V/Wan2_1-I2V-14B-480p_fp8_e4m3fn_scaled_KJ.safetensors
Normal file
3
I2V/Wan2_1-I2V-14B-480p_fp8_e4m3fn_scaled_KJ.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff403000e88bc94ad20d8f118cd8abb7e2d1b2f473610d5e28b7d4cf94a0ab1a
|
||||
size 136
|
||||
3
I2V/Wan2_1-I2V-14B-480p_fp8_e5m2_scaled_KJ.safetensors
Normal file
3
I2V/Wan2_1-I2V-14B-480p_fp8_e5m2_scaled_KJ.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9d042131725e265580d971c6fe34b9f0225e200d53ef8389191f11a88af5ed0a
|
||||
size 136
|
||||
56
README.md
56
README.md
@ -1,47 +1,17 @@
|
||||
---
|
||||
license: Apache License 2.0
|
||||
|
||||
#model-type:
|
||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||||
#- gpt
|
||||
|
||||
#domain:
|
||||
##如 nlp、cv、audio、multi-modal
|
||||
#- nlp
|
||||
|
||||
#language:
|
||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||||
#- cn
|
||||
|
||||
#metrics:
|
||||
##如 CIDEr、Blue、ROUGE 等
|
||||
#- CIDEr
|
||||
|
||||
#tags:
|
||||
##各种自定义,包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||||
#- pretrained
|
||||
|
||||
#tools:
|
||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||||
#- vllm
|
||||
license: apache-2.0
|
||||
---
|
||||
base_model:
|
||||
- Wan-AI/Wan2.1-VACE-14B
|
||||
- Wan-AI/Wan2.1-VACE-1.3B
|
||||
---
|
||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重,可浏览“模型文件”页面获取。
|
||||
#### 您可以通过如下git clone命令,或者ModelScope SDK来下载模型
|
||||
|
||||
SDK下载
|
||||
```bash
|
||||
#安装ModelScope
|
||||
pip install modelscope
|
||||
```
|
||||
```python
|
||||
#SDK模型下载
|
||||
from modelscope import snapshot_download
|
||||
model_dir = snapshot_download('Kijai/WanVideo_comfy_fp8_scaled')
|
||||
```
|
||||
Git下载
|
||||
```
|
||||
#Git模型下载
|
||||
git clone https://www.modelscope.cn/Kijai/WanVideo_comfy_fp8_scaled.git
|
||||
```
|
||||
Better fp8 scaled models (when measured against fp16) based on quantization code from https://github.com/Tencent-Hunyuan/HunyuanVideo/blob/main/hyvideo/modules/fp8_optimization.py
|
||||
|
||||
Can be used with: https://github.com/kijai/ComfyUI-WanVideoWrapper (latest version) and ComfyUI native WanVideo nodes.
|
||||
|
||||
14B-T2V comparison test without LoRAs, 25 steps, 832x480x81
|
||||
---
|
||||
|
||||
<video controls autoplay width=50% src=https://cdn-uploads.huggingface.co/production/uploads/63297908f0b2fc94904a65b8/DwlAGbj20it1unZW54NDC.mp4></video>
|
||||
|
||||
<p style="color: lightgrey;">如果您是本模型的贡献者,我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>,及时完善模型卡片内容。</p>
|
||||
3
T2V/Wan2_1-T2V-14B_fp8_e4m3fn_scaled_KJ.safetensors
Normal file
3
T2V/Wan2_1-T2V-14B_fp8_e4m3fn_scaled_KJ.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b33ef2501a7ac368446c7c8ddcea7f950fd85563a7eebe5018376644053c7553
|
||||
size 136
|
||||
3
T2V/Wan2_1-T2V-14B_fp8_e5m2_scaled_KJ.safetensors
Normal file
3
T2V/Wan2_1-T2V-14B_fp8_e5m2_scaled_KJ.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2ee52d1c67e58ed57339330dcb67ad985cd09d7918677e8bd2ae280a52f5615
|
||||
size 136
|
||||
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a7613b86abbde3d437e8574f0b4ea20c4e408ffc260a4fbfc6ba18b6c9ed1241
|
||||
size 135
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||
Reference in New Issue
Block a user