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.
Concept Sliders for Precise Control of Diffusion Models
| Date | Stars |
|---|---|
| 2026-07-31 | 1136 |
| 2026-08-06 | 1138 |
Today
+2 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Concept Sliders ### [Project Website](https://sliders.baulab.info) | [Arxiv Preprint](https://arxiv.org/pdf/2311.12092.pdf) | [Trained Sliders](https://sliders.baulab.info/weights/xl_sliders/) | [Colab Demo](https://colab.research.google.com/github/rohitgandikota/sliders/blob/main/demo_concept_sliders.ipynb) | [Huggingface Demo](https://huggingface.co/spaces/baulab/ConceptSliders) <br> Official code implementation of "Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models", European Conference on Computer Vision (ECCV 2024). ## 🎉 LATEST UPDATE: SliderSpace 🎉 Experience the next evolution in concept sliders! **SliderSpace** automatically extracts hundreds of sliders from diffusion models' creative knowledge - no training required! Unlock unprecedented creativity with zero effort. <br> [Check out SliderSpace repo](https://github.com/rohitgandikota/sliderspace) 🚀🎨✨ <div align='center'> <img src = 'images/main_figure.png'> </div> ## Colab Demo Try out our colab demo here [](https://colab.research.google.com/github/rohitgandikota/sliders/blob/main/demo_concept_sliders.ipynb) ## FLUX Support 🚀🚀🚀 You can train sliders for FLUX-1 models. Right now it is experimental! Please be patient if it doesn't work as good as SDXL. FLUX is not designed the same way as SDXL. <br> To play with flux sliders you need to update your packages. ``` pip install -r flux-sliders/flux-requirements.txt ``` Now just open the notebook present in the folder `flux-sliders` and have fun! ## UPDATE You can now use GPT-4 (or any other openAI model) to create prompts for your text sliders. All you need to do is describe what slider you want to create (e.g: "i want to make people look happy"). <br> Please refer to the [GPT-notebook](https://github.com/rohitgandikota/sliders/blob/main/GPT_prompt_helper.ipynb) ## Setup To set up your python environment: ``` conda create -n sliders python=3.9 conda activate sliders git clone https://github.com/rohitgandikota/sliders.git cd sliders pip install -r requirements.txt ``` If you are running on Windows - please refer to these Windows setup guidelines [here](https://github.com/rohitgandikota/sliders/issues/27#issuecomment-1833572579) ## Textual Concept Sliders ### Training SD-1.x and SD-2.x LoRa To train an age slider - go to `train-scripts/textsliders/data/prompts.yaml` and edit the `target=person` and `positive=old person` and `unconditional=young person` (opposite of positive) and `neutral=person` and `action=enhance` with `guidance=4`. <br> If you do not want your edit to be targetted to person replace it with any target you want (eg. dog) or if you need it global replace `person` with `""` <br> Finally, run the command: ``` python trainscripts/textsliders/train_lora.py --attributes 'male, female' --name 'ageslider' --rank 4 --alpha 1 --config_file 'trainscripts/textsliders/data/config.yaml' ``` `--attributes` argument is used to disentangle concepts from the slider. For instance age slider makes all old people male (so instead add the `"female, male"` attributes to allow disentanglement) #### Evaluate To evaluate your trained models use the notebook `SD1-sliders-inference.ipynb` ### Training SD-XL To train sliders for SD-XL, use the script `train_lora_xl.py`. The setup is same as SDv1.4 ``` python trainscripts/textsliders/train_lora_xl.py --attributes 'male, female' --name 'agesliderXL' --rank 4 --alpha 1 --config_file 'trainscripts/textsliders/data/config-xl.yaml' ``` #### Evaluate To evaluate your trained models use the notebook `XL-sliders-inference.ipynb` ## Visual Concept Sliders ### Training SD-1.x and SD-2.x LoRa To train image based sliders, you need to create a ~4-6 pairs of image dataset (before/after edit for desired concept). Save the before images and after images separately. You can also create a dataset with varied intensity effect and save them differently. To train an image slider
Excerpt of 6,729 characters
Read on GitHub
84
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3e488db2571ce3f5, llm:Repository title and description: 'Concept Sliders for Precise Control of Diffusion Models' — suggests tooling for controlling diffusion generative models (concept sliders).
matched fp:3e488db2571ce3f5, llm:Repository title and description: 'Concept Sliders for Precise Control of Diffusion Models' — suggests tooling for controlling diffusion generative models (concept sliders).
matched fp:3e488db2571ce3f5, llm:Repository title and description: 'Concept Sliders for Precise Control of Diffusion Models' — suggests tooling for controlling diffusion generative models (concept sliders).