Downloads · 30 days
3
3% of all-time downloads
naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs
ddpm-celebahq-finetuned-vintage-face-2epochs is a unconditional image generation model from naifenn. Use it for the unconditional image generation task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as mit.
This model was fine-tuned for 2 epochs on the CelebAHQ dataset to generate vintage-style face images.
Downloads · 30 days
3
3% of all-time downloads
All-time downloads
113
Public
Parameters
114M
457 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors455 MB · 100%
From the Hugging Face model README
This model was fine-tuned for 2 epochs on the CelebAHQ dataset to generate vintage-style face images.
The image below shows the generation process from pure noise (left) to the final face (right), captured every 10 steps.

from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('naifenn/ddpm-celebahq-finetuned-vintage-face-2epochs')
image = pipeline(num_inference_steps=50).images[0]
image