Downloads · 30 days
197
9% of all-time downloads
nebulae
nroggendorff/nebulae
nebulae is a unconditional image generation model from nroggendorff. 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.
DDPMNebula is a latent noise-to-image diffusion model capable of generating images of nebulas. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion blog.
All-time downloads
2.1K
Public
Parameters
114M
2.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors909 MB · 66%
At a glance
- Task
- Unconditional Image Generation
- Library
- diffusers
- License
- mit
- Access
- Public
- Created
- Apr 5, 2024
- Updated
- Apr 9, 2024
- SHA
- ab739804
Spaces
Model card
From the Hugging Face model README
Nebulae Model Card
DDPMNebula is a latent noise-to-image diffusion model capable of generating images of nebulas. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion blog.
You can use this with the 🧨Diffusers library from Hugging Face.
Diffusers
from diffusers import DiffusionPipeline
pipeline = DiffusionPipeline.from_pretrained("nroggendorff/nebulae")
pipe = pipeline.to("cuda")
image = pipe().images[0]
image.save("nebula.png")
Model Details
train_batch_size: 16eval_batch_size: 16num_epochs: 50gradient_accumulation_steps: 1learning_rate: 1e-4lr_warmup_steps: 500mixed_precision: "fp16"eval_metric: "mean_squared_error"
Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model was trained on a medium-to-large-scale dataset: Nebulae
Developed by
- Noa Linden Roggendorff
This model card was written by Noa Roggendorff and is based on the Stable Diffusion v1-5 Model Card.
- Task
- Unconditional Image Generation
- Library
- diffusers
- License
- mit
- Created
- Apr 5, 2024
- Updated
- Apr 9, 2024