Some tweaks
Browse files
README.md
CHANGED
|
@@ -21,23 +21,23 @@ We host public weights for Latent Diffusion and Stable Diffusion models. There a
|
|
| 21 |
</p>
|
| 22 |
|
| 23 |
<p>
|
| 24 |
-
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion works, please have a look at
|
| 25 |
</p>
|
| 26 |
|
| 27 |
<p>
|
| 28 |
We recommend you use Stable Diffusion with <a href="https://github.com/huggingface/diffusers">🤗 Diffusers library</a>. You can also use the original <a href="https://github.com/compvis/stable-diffusion">CompVis code</a>. There are variants of the weights depending on:
|
| 29 |
<ul>
|
| 30 |
<li>The library they are intended for.</li>
|
| 31 |
-
<li>The training regime. There are 4 training versions:
|
| 32 |
</p>
|
| 33 |
|
| 34 |
<p>
|
| 35 |
Please, refer to the details in the following table to choose the weights appropriate for your use.
|
| 36 |
</p>
|
| 37 |
|
| 38 |
-
| Model | Library
|
| 39 |
-
|
| 40 |
-
| stable-diffusion-v1-1
|
| 41 |
| stable-diffusion-v1-2 | Diffusers | v1-1 plus: 515k steps at 512x512 on "laion-improved-aesthetics". |
|
| 42 |
| stable-diffusion-v1-3 | Diffusers | v1-2 plus: 195k steps at 512x512 on "laion-improved-aesthetics",with 10% dropping of text-conditioning. |
|
| 43 |
| stable-diffusion-v1-4 | Diffusers | |
|
|
|
|
| 21 |
</p>
|
| 22 |
|
| 23 |
<p>
|
| 24 |
+
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion works, please have a look at <a href="https://hf.co/blog/stable_diffusion">🤗's Stable Diffusion with 🧨 Diffusers blog.
|
| 25 |
</p>
|
| 26 |
|
| 27 |
<p>
|
| 28 |
We recommend you use Stable Diffusion with <a href="https://github.com/huggingface/diffusers">🤗 Diffusers library</a>. You can also use the original <a href="https://github.com/compvis/stable-diffusion">CompVis code</a>. There are variants of the weights depending on:
|
| 29 |
<ul>
|
| 30 |
<li>The library they are intended for.</li>
|
| 31 |
+
<li>The training regime. There are 4 training versions: <tt>v1-1</tt> through <tt>v1-4</tt>. Each one was created from the checkpoint of the previous version, and was trained for additional steps in specific variants of the dataset.
|
| 32 |
</p>
|
| 33 |
|
| 34 |
<p>
|
| 35 |
Please, refer to the details in the following table to choose the weights appropriate for your use.
|
| 36 |
</p>
|
| 37 |
|
| 38 |
+
| Model | Library | Details |
|
| 39 |
+
|--------------------------------|-------------|------------------------------------------------------------------------------------------------------------|
|
| 40 |
+
| [stable-diffusion-v1-1](https://huggingface.co/CompVis/stable-diffusion-v1-1) | 🤗 Diffusers | 237k steps at resolution 256x256 on laion2B-en. 194k steps at resolution 512x512 on laion-high-resolution. |
|
| 41 |
| stable-diffusion-v1-2 | Diffusers | v1-1 plus: 515k steps at 512x512 on "laion-improved-aesthetics". |
|
| 42 |
| stable-diffusion-v1-3 | Diffusers | v1-2 plus: 195k steps at 512x512 on "laion-improved-aesthetics",with 10% dropping of text-conditioning. |
|
| 43 |
| stable-diffusion-v1-4 | Diffusers | |
|