| |
|
| | --- |
| | license: creativeml-openrail-m |
| | base_model: stabilityai/stable-diffusion-xl-base-1.0 |
| | dataset: NYUAD-ComNets/Black_Female_Profession |
| | tags: |
| | - stable-diffusion-xl |
| | - stable-diffusion-xl-diffusers |
| | - text-to-image |
| | - diffusers |
| | - lora |
| | inference: true |
| | --- |
| | |
| | # Model description |
| | |
| | This model is a part of project targeting Debiasing of generative stable diffusion models. |
| |
|
| | LoRA text2image fine-tuning - NYUAD-ComNets/Black_Female_Profession_Model |
| | |
| | These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the NYUAD-ComNets/Black_Female_Profession dataset. |
| | You can find some example images. |
| | |
| | prompt: a photo of a {profession}, looking at the camera, closeup headshot facing forward, ultra quality, sharp focus |
| | |
| | # How to use this model: |
| | |
| | ``` python |
| | |
| | |
| | import torch |
| | from compel import Compel, ReturnedEmbeddingsType |
| | from diffusers import DiffusionPipeline |
| | |
| | import random |
| | |
| | |
| | negative_prompt = "cartoon, anime, 3d, painting, b&w, low quality" |
| |
|
| |
|
| | models=["NYUAD-ComNets/Asian_Female_Profession_Model","NYUAD-ComNets/Black_Female_Profession_Model","NYUAD-ComNets/White_Female_Profession_Model", |
| | "NYUAD-ComNets/Indian_Female_Profession_Model","NYUAD-ComNets/Latino_Hispanic_Female_Profession_Model","NYUAD-ComNets/Middle_Eastern_Female_Profession_Model", |
| | "NYUAD-ComNets/Asian_Male_Profession_Model","NYUAD-ComNets/Black_Male_Profession_Model","NYUAD-ComNets/White_Male_Profession_Model", |
| | "NYUAD-ComNets/Indian_Male_Profession_Model","NYUAD-ComNets/Latino_Hispanic_Male_Profession_Model","NYUAD-ComNets/Middle_Eastern_Male_Profession_Model"] |
| |
|
| | adapters=["asian_female","black_female","white_female","indian_female","latino_female","middle_east_female", |
| | "asian_male","black_male","white_male","indian_male","latino_male","middle_east_male"] |
| |
|
| | pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", variant="fp16", use_safetensors=True, torch_dtype=torch.float16).to("cuda") |
| | |
| | |
| | for i,j in zip(models,adapters): |
| | pipeline.load_lora_weights(i, weight_name="pytorch_lora_weights.safetensors",adapter_name=j) |
| | |
| | |
| | prof='doctor' |
| | |
| | |
| | pipeline.set_adapters(random.choice(adapters)) |
| |
|
| |
|
| | compel = Compel(tokenizer=[pipeline.tokenizer, pipeline.tokenizer_2] , |
| | text_encoder=[pipeline.text_encoder, pipeline.text_encoder_2], |
| | returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED, |
| | requires_pooled=[False, True],truncate_long_prompts=False) |
| |
|
| | |
| | conditioning, pooled = compel("a photo of a {}, looking at the camera, closeup headshot facing forward, ultra quality, sharp focus".format(prof)) |
| | |
| | negative_conditioning, negative_pooled = compel(negative_prompt) |
| | [conditioning, negative_conditioning] = compel.pad_conditioning_tensors_to_same_length([conditioning, negative_conditioning]) |
| |
|
| | image = pipeline(prompt_embeds=conditioning, negative_prompt_embeds=negative_conditioning, |
| | pooled_prompt_embeds=pooled, negative_pooled_prompt_embeds=negative_pooled, |
| | num_inference_steps=40).images[0] |
| | |
| | image.save('/../../x.jpg') |
| |
|
| | ``` |
| | |
| | |
| | # Examples |
| | |
| | | | | | |
| | |:-------------------------:|:-------------------------:|:-------------------------:| |
| | |<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./18.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./349.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./710.jpg">| |
| | |<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./230.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./5.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./83.jpg">| |
| | |<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./278.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./539.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./90.jpg">| |
| | |<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./30.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./596.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./1061.jpg">| |
| | |
| | |
| | |
| | |
| | # Training data |
| | |
| | NYUAD-ComNets/Black_Female_Profession dataset was used to fine-tune stabilityai/stable-diffusion-xl-base-1.0 |
| | |
| | |
| | |
| | # Configurations |
| | |
| | LoRA for the text encoder was enabled: False. |
| | |
| | Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. |
| | |
| | |
| | |
| | # BibTeX entry and citation info |
| | |
| | ``` |
| | @article{aldahoul2025ai, |
| | title={AI-generated faces influence gender stereotypes and racial homogenization}, |
| | author={AlDahoul, Nouar and Rahwan, Talal and Zaki, Yasir}, |
| | journal={Scientific reports}, |
| | volume={15}, |
| | number={1}, |
| | pages={14449}, |
| | year={2025}, |
| | publisher={Nature Publishing Group UK London} |
| | } |
| |
|
| | @article{aldahoul2024ai, |
| | title={AI-generated faces free from racial and gender stereotypes}, |
| | author={AlDahoul, Nouar and Rahwan, Talal and Zaki, Yasir}, |
| | journal={arXiv preprint arXiv:2402.01002}, |
| | year={2024} |
| | } |
| |
|
| | @misc{ComNets, |
| | url={[https://huggingface.co/NYUAD-ComNets/Black_Female_Profession_Model](https://huggingface.co/NYUAD-ComNets/Black_Female_Profession_Model)}, |
| | title={Black_Female_Profession_Model}, |
| | author={Nouar AlDahoul, Talal Rahwan, Yasir Zaki} |
| | } |
| | ``` |
