Downloads · 30 days
7
1% of all-time downloads
latent_32_ga-8
Likalto4/latent_32_ga-8
latent_32_ga-8 is a unconditional image generation model from Likalto4. 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 is a latent diffusion model for generation of mammograms with size 64x64 in the latent space. It was trained with 4K images in the latent space (10% of the original dataset) for 50 epochs. Images in the latent sp…
All-time downloads
766
Public
Repo size
910 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin455 MB · 100%
At a glance
- Task
- Unconditional Image Generation
- Library
- diffusers
- License
- mit
- Access
- Public
- Created
- Mar 9, 2023
- Updated
- Mar 14, 2023
- SHA
- 564aed87
Model card
From the Hugging Face model README
This is a latent diffusion model for generation of mammograms with size 64x64 in the latent space. It was trained with 4K images in the latent space (10% of the original dataset) for 50 epochs. Images in the latent space have size (4,64,64) and can generate images of 512x512 when decoded using the VAE.
Usage
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained({hub_model_id})
image = pipeline().images[0]
image
- Task
- Unconditional Image Generation
- Library
- diffusers
- License
- mit
- Created
- Mar 9, 2023
- Updated
- Mar 14, 2023