Spaces:
Running
Running
Commit
•
d7a8807
1
Parent(s):
5d114a6
Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,38 @@ sdk: static
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
+
# Welcome to the 🧨 `diffusers` organization!
|
11 |
+
`diffusers` is the go-to library for state-of-the-art pretrained diffusion models for multi-modal generative AI. You can use it on [GitHub](https://github.com/huggingface/diffusers).
|
12 |
+
|
13 |
+
In this organization, you can find some utilities and models the diffusers team has made for you 🫶
|
14 |
+
|
15 |
+
## 🆕 SDXL ControlNets
|
16 |
+
The `diffusers` team is training ControlNets for Stable Diffusion XL
|
17 |
+
|
18 |
+
### Small sized ControlNets
|
19 |
+
|
20 |
+
The team is experimenting with training smaller ControlNets that can still retain their control capabilities. This is the [training script used](https://github.com/huggingface/diffusers/blob/7b93c2a882d8e12209fbaeffa51ee2b599ab5349/examples/research_projects/controlnet/train_controlnet_webdataset.py).
|
21 |
+
Check out some of the models released, and please provide us with feedback on what you thought about them on our [Discord server](https://t.co/1n75wi976V?amp=1)
|
22 |
+
|
23 |
+
| ControlNet | Size in fp16 |
|
24 |
+
|-----------------------------------|---------------|
|
25 |
+
| [`controlnet-canny-sdxl-1.0-small`](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0-small) | 320MB |
|
26 |
+
| [`controlnet-canny-sdxl-1.0-mid`](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0-mid) | 545MB |
|
27 |
+
| [`controlnet-depth-sdxl-1.0-small`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0-small) | 320MB |
|
28 |
+
| [`controlnet-depth-sdxl-1.0-mid`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0-mid) | 545MB |
|
29 |
+
|
30 |
+
### Full sized ControlNets
|
31 |
+
|
32 |
+
The team has also trained full sized ControlNets - as big as the SDXL model (5GB in fp32). We have provided a [ControlNet training script and guide here](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md)
|
33 |
+
|
34 |
+
| ControlNet |
|
35 |
+
|-----------------------------------|
|
36 |
+
| [`controlnet-canny-sdxl-1.0`](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0) |
|
37 |
+
| [`controlnet-depth-sdxl-1.0`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0) |
|
38 |
+
|
39 |
+
### Utilities
|
40 |
+
- [Convert Stable Diffusion XL weights to `diffusers` format](https://huggingface.co/spaces/diffusers/sdxl-to-diffusers)
|
41 |
+
- [Convert Stable Diffusion weights to `diffusers` format](https://huggingface.co/spaces/diffusers/sd-to-diffusers)
|
42 |
+
- [Convert diffusers models to `safetensors` format](https://huggingface.co/spaces/diffusers/convert)
|
43 |
+
|
44 |
+
More coming soon ✨
|