Spaces:
Running
Running
Commit
·
eb1e6c1
1
Parent(s):
4c99e2d
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,12 +14,12 @@ pinned: false
|
|
| 14 |
|
| 15 |
In this organization, you can find some utilities and models the diffusers team has made for you 🫶
|
| 16 |
|
| 17 |
-
## 🆕 SDXL ControlNets
|
| 18 |
The `diffusers` team is training ControlNets for Stable Diffusion XL
|
| 19 |
|
| 20 |
-
### Small sized ControlNets
|
| 21 |
|
| 22 |
-
We are experimenting with training smaller ControlNets
|
| 23 |
Please check the models released, and consider giving us feedback on our [Discord server](https://t.co/1n75wi976V?amp=1):
|
| 24 |
|
| 25 |
| ControlNet | Size in fp16 |
|
|
@@ -29,7 +29,7 @@ Please check the models released, and consider giving us feedback on our [Discor
|
|
| 29 |
| [`controlnet-depth-sdxl-1.0-small`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0-small) | 320MB |
|
| 30 |
| [`controlnet-depth-sdxl-1.0-mid`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0-mid) | 545MB |
|
| 31 |
|
| 32 |
-
### Full sized ControlNets
|
| 33 |
|
| 34 |
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)
|
| 35 |
|
|
@@ -38,7 +38,7 @@ The team has also trained full sized ControlNets - as big as the SDXL model (5GB
|
|
| 38 |
| [`controlnet-canny-sdxl-1.0`](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0) |
|
| 39 |
| [`controlnet-depth-sdxl-1.0`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0) |
|
| 40 |
|
| 41 |
-
### Utilities
|
| 42 |
- [Convert Stable Diffusion XL weights to `diffusers` format](https://huggingface.co/spaces/diffusers/sdxl-to-diffusers)
|
| 43 |
- [Convert Stable Diffusion weights to `diffusers` format](https://huggingface.co/spaces/diffusers/sd-to-diffusers)
|
| 44 |
- [Convert diffusers models to `safetensors` format](https://huggingface.co/spaces/diffusers/convert)
|
|
|
|
| 14 |
|
| 15 |
In this organization, you can find some utilities and models the diffusers team has made for you 🫶
|
| 16 |
|
| 17 |
+
## 🆕 SDXL ControlNets
|
| 18 |
The `diffusers` team is training ControlNets for Stable Diffusion XL
|
| 19 |
|
| 20 |
+
### Small sized ControlNets 🤏
|
| 21 |
|
| 22 |
+
We are 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).
|
| 23 |
Please check the models released, and consider giving us feedback on our [Discord server](https://t.co/1n75wi976V?amp=1):
|
| 24 |
|
| 25 |
| ControlNet | Size in fp16 |
|
|
|
|
| 29 |
| [`controlnet-depth-sdxl-1.0-small`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0-small) | 320MB |
|
| 30 |
| [`controlnet-depth-sdxl-1.0-mid`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0-mid) | 545MB |
|
| 31 |
|
| 32 |
+
### Full sized ControlNets 💪
|
| 33 |
|
| 34 |
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)
|
| 35 |
|
|
|
|
| 38 |
| [`controlnet-canny-sdxl-1.0`](https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0) |
|
| 39 |
| [`controlnet-depth-sdxl-1.0`](https://huggingface.co/diffusers/controlnet-depth-sdxl-1.0) |
|
| 40 |
|
| 41 |
+
### Utilities 🔧
|
| 42 |
- [Convert Stable Diffusion XL weights to `diffusers` format](https://huggingface.co/spaces/diffusers/sdxl-to-diffusers)
|
| 43 |
- [Convert Stable Diffusion weights to `diffusers` format](https://huggingface.co/spaces/diffusers/sd-to-diffusers)
|
| 44 |
- [Convert diffusers models to `safetensors` format](https://huggingface.co/spaces/diffusers/convert)
|