Commit ·
da4e4ae
1
Parent(s): 69692b2
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,8 @@ checkpoint and subsequently fine-tuned on 515,000 steps at resolution `512x512`
|
|
| 29 |
filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`.
|
| 30 |
For more information, please refer to [Training](#training).
|
| 31 |
|
|
|
|
|
|
|
| 32 |
## Model Details
|
| 33 |
- **Developed by:** Robin Rombach, Patrick Esser
|
| 34 |
- **Model type:** Diffusion-based text-to-image generation model
|
|
|
|
| 29 |
filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`.
|
| 30 |
For more information, please refer to [Training](#training).
|
| 31 |
|
| 32 |
+
This weights here are intended to be used with the D🧨iffusers library. If you are looking for the weights to be loaded into the CompVis Stable Diffusion codebase, [come here](https://huggingface.co/CompVis/stable-diffusion-v-1-2-original)
|
| 33 |
+
|
| 34 |
## Model Details
|
| 35 |
- **Developed by:** Robin Rombach, Patrick Esser
|
| 36 |
- **Model type:** Diffusion-based text-to-image generation model
|