|
|
|
--- |
|
license: creativeml-openrail-m |
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
dataset: NYUAD-ComNets/Middle_Eastern_Male_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/Middle_Eastern_Male_Profession_Model |
|
|
|
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the NYUAD-ComNets/Middle_Eastern_Male_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: |
|
|
|
|
|
``` API |
|
|
|
import requests |
|
|
|
API_URL = "https://api-inference.huggingface.co/models/NYUAD-ComNets/Middle_Eastern_Male_Profession_Model" |
|
headers = {"Authorization": "Bearer {hugging_face token}"} |
|
|
|
def query(payload): |
|
response = requests.post(API_URL, headers=headers, json=payload) |
|
return response.content |
|
|
|
image_bytes = query({ |
|
"inputs": "a headshot of a person with green hair and eyeglasses", |
|
"parameters": {"negative_prompt": "cartoon", |
|
"seed":766}, |
|
}) |
|
# You can access the image with PIL.Image for example |
|
import io |
|
from PIL import Image |
|
image = Image.open(io.BytesIO(image_bytes)) |
|
image |
|
|
|
``` |
|
|
|
|
|
``` 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) |
|
|
|
|
|
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 doctor, looking at the camera, closeup headshot facing forward, ultra quality, sharp focus") |
|
|
|
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="./1064.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./1610.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./292.jpg">| |
|
|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./1191.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./1699.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./581.jpg">| |
|
|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./1399.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./2073.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./50.jpg">| |
|
|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./1519.jpg"> | <img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./234.jpg">|<img width="500" alt="screen shot 2017-08-07 at 12 18 15 pm" src="./971.jpg">| |
|
|
|
|
|
|
|
|
|
# Training data |
|
|
|
NYUAD-ComNets/Middle_Eastern_Male_Profession dataset was used to fine-tune stabilityai/stable-diffusion-xl-base-1.0 |
|
|
|
profession list =['pilot','doctor','nurse','pharmacist','dietitian','professor','teacher','mathematics scientist','computer engineer','programmer','tailor','cleaner', |
|
'soldier','security guard','lawyer','manager','accountant','secretary','singer','journalist','youtuber','tiktoker','fashion model','chef','sushi chef'] |
|
|
|
# Configurations |
|
|
|
LoRA for the text encoder was enabled: False. |
|
|
|
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. |
|
|
|
|
|
|
|
# BibTeX entry and citation info |
|
|
|
``` |
|
@misc{ComNets, |
|
url={[https://huggingface.co/NYUAD-ComNets/Middle_Eastern_Male_Profession_Model](https://huggingface.co/NYUAD-ComNets/Middle_Eastern_Male_Profession_Model)}, |
|
title={Middle_Eastern_Male_Profession_Model}, |
|
author={Nouar AlDahoul, Talal Rahwan, Yasir Zaki} |
|
} |
|
``` |
|
|
|
|