imnotednamode
commited on
Commit
•
1b53737
1
Parent(s):
91a72e1
Update README.md
Browse files
README.md
CHANGED
@@ -4,6 +4,8 @@ base_model:
|
|
4 |
- genmo/mochi-1-preview
|
5 |
---
|
6 |
|
|
|
|
|
7 |
This mixes mochi with a development version of diffusers to achieve high quality fast inference with the full 161 frames on a single 24gb card. This repo contains only the transformer. After installing the mochi development branch with `pip install git+https://github.com/huggingface/diffusers@mochi`, it can be loaded normally and used in a pipeline like so:
|
8 |
```
|
9 |
from diffusers import MochiPipeline, MochiTransformer3DModel
|
|
|
4 |
- genmo/mochi-1-preview
|
5 |
---
|
6 |
|
7 |
+
**Still not small enough? Try https://huggingface.co/imnotednamode/mochi-1-preview-mix-nf4-small**
|
8 |
+
|
9 |
This mixes mochi with a development version of diffusers to achieve high quality fast inference with the full 161 frames on a single 24gb card. This repo contains only the transformer. After installing the mochi development branch with `pip install git+https://github.com/huggingface/diffusers@mochi`, it can be loaded normally and used in a pipeline like so:
|
10 |
```
|
11 |
from diffusers import MochiPipeline, MochiTransformer3DModel
|