Skip to content

Commit 4345c28

Browse files
Nupur KumariNupur Kumari
authored andcommitted
update readme
1 parent ca18330 commit 4345c28

File tree

2 files changed

+9
-3
lines changed

2 files changed

+9
-3
lines changed

README.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,12 @@
11
# Custom Diffusion
22

3-
### [website](https://www.cs.cmu.edu/~custom-diffusion/) | [paper](http://arxiv.org/abs/2212.04488) | [gradio demo](https://huggingface.co/spaces/nupurkmr9/custom-diffusion)
3+
### [website](https://www.cs.cmu.edu/~custom-diffusion/) | [paper](http://arxiv.org/abs/2212.04488)
44

55

66
**[NEW!]** Custom Diffusion is now supported in diffusers. Please [refer](https://github.com/huggingface/diffusers/tree/main/examples/custom_diffusion) here for training and inference details.
77

8+
**[NEW!]** CustomConcept101 dataset. We release a new dataset of 101 concepts along with their evaluation prompts. For more details please refer [here](customconcept101/README.md).
9+
810

911
<br>
1012
<div class="gif">

customconcept101/README.md

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# CustomConcept101
22

3-
We release a dataset of 101 concepts with 3-15 images for each concept for evaluating model customization methods. For a more detailed view target images please refer to our [webpage](https://www.cs.cmu.edu/~custom-diffusion/dataset.html).
3+
We release a dataset of 101 concepts with 3-15 images for each concept for evaluating model customization methods. For a more detailed view of target images please refer to our [webpage](https://www.cs.cmu.edu/~custom-diffusion/dataset.html).
44

55
<br>
66
<div>
@@ -128,9 +128,13 @@ We compare our method (Custom Diffusion) with [DreamBooth](https://dreambooth.gi
128128
</tr>
129129
</table>
130130

131+
## Evaluation prompts
132+
We used ChatGPT to generate 40 image captions for each concept with the instructions to either (1) change the background of the scene while keeping the main subject, (2) insert a new object/living thing in the scene along with the main subject, (3) style variation of the main subject, and (4) change the property or material of the main subject. The generated text prompts are manually filtered or modified to get the final 20 prompts for each concept. A similar strategy is applied for multiple concepts. Some of the prompts are also inspired by other concurrent works e.g. [Perfusion](https://research.nvidia.com/labs/par/Perfusion/), [DreamBooth](https://dreambooth.github.io), [SuTI](https://open-vision-language.github.io/suti/), [BLIP-Diffusion](https://dxli94.github.io/BLIP-Diffusion-website/) etc.
133+
134+
131135

132136
## License
133-
Images taken from UnSplash are under [Unsplash License](https://unsplash.com/license). Images captured by ourselves are released under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/deed.en) license. Flower category images are downloaded from Wikimedia/Flickr/Pixabay and the link to orginial images can be found [here](https://www.cs.cmu.edu/~custom-diffusion/assets/urls.txt).
137+
Images taken from UnSplash are under [Unsplash License](https://unsplash.com/license). Images captured by ourselves are released under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/deed.en) license. Flower category images are downloaded from Wikimedia/Flickr/Pixabay and the link to orginial images can also be found [here](https://www.cs.cmu.edu/~custom-diffusion/assets/urls.txt) for attribution.
134138

135139

136140
## Acknowledgments

0 commit comments

Comments
 (0)