Mukh-Oboyob
Adapted from official Github repository: https://github.com/Codernob/Mukh-Oboyob
- Huggingface spaces: https://huggingface.co/spaces/gr33nr1ng3r/Mukh-Oboyob
Usage
from diffusers import DiffusionPipeline
device="cuda"
pipeline = DiffusionPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
custom_pipeline="ahmedfaiyaz/Mukh-Oboyob"
)
pipeline.unet.load_attn_procs("gr33nr1ng3r/Mukh-Oboyob")
pipeline.to(device)
prompt = "মেয়েটির কালো চুল ছিল। মেয়েটির মুখে ভারী মেকাপ ছিল। মেয়েটির উঁচু গালের হাড় ছিল। মেয়েটির মুখ কিছুটা খোলা ছিল। মেয়েটির চেহারা ডিম্বাকৃতির। মেয়েটির চোখা নাক ছিল। মেয়েটির ঢেউ খেলানো চুল ছিল। মেয়েটির কানে দুল পরা ছিল। মেয়েটির লিপস্টিক পরা ছিল। "
image = pipeline(prompt, num_inference_steps=200, guidance_scale=7.5,height=128,width=128).images[0]
image
Download model
Weights for this model are available in PyTorch format.
Download them in the Files & versions tab.
Citation
If you use any of the models or code,please cite the following paper:
@article{Saha2023,
title = {Mukh-Oboyob: Stable Diffusion and BanglaBERT enhanced Bangla Text-to-Face Synthesis},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2023.01411142},
url = {http://dx.doi.org/10.14569/IJACSA.2023.01411142},
year = {2023},
publisher = {The Science and Information Organization},
volume = {14},
number = {11},
author = {Aloke Kumar Saha and Noor Mairukh Khan Arnob and Nakiba Nuren Rahman and Maria Haque and Shah Murtaza Rashid Al Masud and Rashik Rahman}
}
- Downloads last month
- 104
Model tree for ahmedfaiyaz/Mukh-Oboyob
Base model
CompVis/stable-diffusion-v1-4