Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ This repository contains a model that generates highly aesthetic images of resol
|
|
19 |
|
20 |
Playground v2.5 is the state-of-the-art open-source model in aesthetic quality. Our user studies demonstrate that our model outperforms SDXL, Playground v2, PIXART-α, DALL-E 3, and Midjourney 5.2.
|
21 |
|
22 |
-
For details on the development and training of our model, please refer to our blog post [link] and technical report [link]
|
23 |
|
24 |
### Model Description
|
25 |
- **Developed by:** [Playground](https://playground.com)
|
@@ -28,14 +28,14 @@ For details on the development and training of our model, please refer to our bl
|
|
28 |
- **Summary:** This model generates images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pre-trained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L). It follows the same architecture as [Stable Diffusion XL](https://huggingface.co/docs/diffusers/en/using-diffusers/sdxl).
|
29 |
|
30 |
### Using the model with 🧨 Diffusers
|
31 |
-
TODO
|
32 |
|
33 |
### Using the model with Automatic1111/ComfyUI
|
34 |
-
TODO
|
35 |
|
36 |
### User Studies
|
37 |
|
38 |
-
This model card only provides a brief summary of our user study results. For extensive details on how we perform user studies, please check out our technical report: [link]
|
39 |
|
40 |
We conducted studies to measure overall aesthetic quality, as well as for the specific areas we aimed to improve with Playground v2.5, namely multi aspect ratios and human preference alignment.
|
41 |
|
@@ -58,9 +58,9 @@ Lastly, we report metrics using our MJHQ-30K benchmark which we [open-sourced](h
|
|
58 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/636c0c4eaae2da3c76b8a9a3/7tyYDPGUtokh-k18XDSte.png)
|
59 |
|
60 |
### How to cite us
|
61 |
-
```
|
62 |
-
// TODO: Link to the technical report
|
63 |
|
|
|
|
|
64 |
@misc{playground-v2.5,
|
65 |
url={[https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic](https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic)},
|
66 |
title={Playground v2.5: Three Insights for Achieving State of the Art in Text-to-Image Generation},
|
|
|
19 |
|
20 |
Playground v2.5 is the state-of-the-art open-source model in aesthetic quality. Our user studies demonstrate that our model outperforms SDXL, Playground v2, PIXART-α, DALL-E 3, and Midjourney 5.2.
|
21 |
|
22 |
+
For details on the development and training of our model, please refer to our blog post <span style="color: red;">[link]</span> and technical report <span style="color: red;">[link]</span>
|
23 |
|
24 |
### Model Description
|
25 |
- **Developed by:** [Playground](https://playground.com)
|
|
|
28 |
- **Summary:** This model generates images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pre-trained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L). It follows the same architecture as [Stable Diffusion XL](https://huggingface.co/docs/diffusers/en/using-diffusers/sdxl).
|
29 |
|
30 |
### Using the model with 🧨 Diffusers
|
31 |
+
<span style="color: red;">TODO</span>
|
32 |
|
33 |
### Using the model with Automatic1111/ComfyUI
|
34 |
+
<span style="color: red;">TODO</span>
|
35 |
|
36 |
### User Studies
|
37 |
|
38 |
+
This model card only provides a brief summary of our user study results. For extensive details on how we perform user studies, please check out our technical report: <span style="color: red;">[link]</span>
|
39 |
|
40 |
We conducted studies to measure overall aesthetic quality, as well as for the specific areas we aimed to improve with Playground v2.5, namely multi aspect ratios and human preference alignment.
|
41 |
|
|
|
58 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/636c0c4eaae2da3c76b8a9a3/7tyYDPGUtokh-k18XDSte.png)
|
59 |
|
60 |
### How to cite us
|
|
|
|
|
61 |
|
62 |
+
<span style="color: red;">TODO: Link to the technical report</span>
|
63 |
+
```
|
64 |
@misc{playground-v2.5,
|
65 |
url={[https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic](https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic)},
|
66 |
title={Playground v2.5: Three Insights for Achieving State of the Art in Text-to-Image Generation},
|