Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Personalization for Stable Diffusion via Aesthetic Gradients 🎨
| Date | Stars |
|---|---|
| 2026-07-24 | 741 |
| 2026-07-25 | 741 |
| 2026-07-28 | 741 |
| 2026-07-30 | 741 |
| 2026-07-31 | 741 |
| 2026-08-06 | 741 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Stable Diffusion with Aesthetic Gradients 🎨 This is the codebase for the article [Personalizing Text-to-Image Generation via Aesthetic Gradients](https://arxiv.org/abs/2209.12330): > This work proposes aesthetic gradients, a method to personalize a CLIP-conditioned diffusion model by guiding the generative process towards custom aesthetics defined by the user from a set of images. The approach is validated with qualitative and quantitative experiments, using the recent stable diffusion model and several aesthetically-filtered datasets. In particular, this reposiory allows the user to use the aesthetic gradients technique described in the previous paper to personalize stable diffusion. ## tl;dr > With this, you don't have to learn a lot of spells/modifiers to improve the quality of the generated image. ## Prerequisites This is a fork of the original stable-diffusion repository, so the prerequisites are the same as the [original repository](https://github.com/CompVis/stable-diffusion/). In particular, when cloning this repo, install the library as: ```bash pip install -e . ``` ## Usage You can use the same arguments as with the original stable diffusion repository. The script `scripts/txt2img.py` has the additional arguments: - `--aesthetic_steps`: number of optimization steps when doing the personalization. For a given prompt, it is recommended to start with few steps (2 or 3), and then gradually increase it (trying 5, 10, 15, 20, etc). The greater the value, the more the resulting image will be biased towards the aesthetic embedding. - `--aesthetic_lr`: learning rate for the aesthetic gradient optimization. The default value is 0.0001. This value almost usually works well enough, so you can just only tune the previous argument. - `--aesthetic_embedding`: path to the stored pytorch tensor (.pt format) containing the aesthetic embedding. It must be of shape 1x768 (CLIP-L/14 size). See below for computing your own aesthetic embeddings. In this repository we include all the aesthetic embeddings used in the paper. All of them are in the directory `aesthetic_embeddings`: * `sac_8plus.pt` * `laion_7plus.pt` * `aivazovsky.pt` * `cloudcore.pt` * `gloomcore.pt` * `glowwave.pt` See the paper to see how they were obtained. In addition, new aesthetic embeddings have been incorporated: * `fantasy.pt`: created from [https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6.5plus](https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6.5plus) by filtering only the images with word "fantasy" in the caption. The top 2000 images by score are selected for the embedding. * `flower_plant.pt`: created from [https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6.5plus](https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6.5plus) by filtering only the images with word "plant", "flower", "floral", "vegetation" or "garden" in the caption. The top 2000 images by score are selected for the embedding. ### Examples Let's see some examples now. This would be with the un-personalized, original SD model: ```bash python scripts/txt2img.py --prompt "Roman city on top of a ridge, sci-fi illustration by Greg Rutkowski #sci-fi detailed vivid colors gothic concept illustration by James Gurney and Zdzislaw Beksiński vivid vivid colorsg concept illustration colorful interior" --seed 332 --plms --aesthetic_steps 0 --W 768 --aesthetic_embedding aesthetic_embeddings/laion_7plus.pt ```  If we now personalize it with the LAION embedding, note how the images get more floral patterns, as this is one common pattern of the LAION aesthetics dataset: ```bash python scripts/txt2img.py --prompt "Roman city on top of a ridge, sci-fi illustration by Greg Rutkowski #sci-fi detailed vivid colors gothic concept illustration by James Gurney and Zdzislaw Beksiński vivid vivid colorsg concept illustration colorful interior" --seed 332 --plms --aesthetic_steps 5
Excerpt of 10,681 characters
Read on GitHub
19
Patrick Esser
7
Robin Rombach
7
Patrick von Platen
6
2
Charles Packer · @letta-ai · United States
1
apolinário
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9c7e8e58fd5daddf, topic:stable-diffusion, topic:diffusion-models, topic:text-to-image