Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,10 @@ SDXS is a model that can generate high-resolution images in real-time based on p
|
|
| 13 |
|
| 14 |
SDXS-512-0.9 is a **old version** of SDXS-512. In order to avoid some possible commercial and copyright risks, the SDXS-512-1.0 and SDXS-1024-1.0 will not be available shortly, and as an alternative we will provide new versions with different teacher DM or offline DM. Watch [our repo](https://github.com/IDKiro/sdxs) for any updates.
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
Model Information:
|
| 17 |
- Teacher DM: [SD Turbo](https://huggingface.co/stabilityai/sd-turbo)
|
| 18 |
- Offline DM: [SD v2.1 base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)
|
|
@@ -23,10 +27,6 @@ The main differences between this model and version 1.0 are in three aspects:
|
|
| 23 |
2. This version did not perform the LoRA-GAN finetune mentioned in the implementation details section, which may result in slightly inferior image details.
|
| 24 |
3. This version replaces self-attention with cross-attention in the highest resolution stages, which introduces minimal overhead compared to directly removing them.
|
| 25 |
|
| 26 |
-
Other versions:
|
| 27 |
-
|
| 28 |
-
- [SDXS-512-DreamShaper](https://huggingface.co/IDKiro/sdxs-512-dreamshaper)
|
| 29 |
-
|
| 30 |
## Diffusers Usage
|
| 31 |
|
| 32 |
|
|
|
|
| 13 |
|
| 14 |
SDXS-512-0.9 is a **old version** of SDXS-512. In order to avoid some possible commercial and copyright risks, the SDXS-512-1.0 and SDXS-1024-1.0 will not be available shortly, and as an alternative we will provide new versions with different teacher DM or offline DM. Watch [our repo](https://github.com/IDKiro/sdxs) for any updates.
|
| 15 |
|
| 16 |
+
**Other versions**:
|
| 17 |
+
|
| 18 |
+
- [SDXS-512-DreamShaper](https://huggingface.co/IDKiro/sdxs-512-dreamshaper): better quality and faster.
|
| 19 |
+
|
| 20 |
Model Information:
|
| 21 |
- Teacher DM: [SD Turbo](https://huggingface.co/stabilityai/sd-turbo)
|
| 22 |
- Offline DM: [SD v2.1 base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)
|
|
|
|
| 27 |
2. This version did not perform the LoRA-GAN finetune mentioned in the implementation details section, which may result in slightly inferior image details.
|
| 28 |
3. This version replaces self-attention with cross-attention in the highest resolution stages, which introduces minimal overhead compared to directly removing them.
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
## Diffusers Usage
|
| 31 |
|
| 32 |
|