Text-to-Image
Diffusers
English
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Inference Endpoints
YAML Metadata Error: "thumbnail" is not allowed to be empty

Hubble Diffusion v1: Stable Diffusion v1.4 fine tuned on ESA Hubble Deep Space Images & Captions

Put in a detailed text prompt and generate Hubble Deep Space Images!

Hubble captures the death of a star: Old stars, nearing the end of their life, collapse under the weight of their own gravity and the outer layers explode as a 'supernova'. In this image Hubble captures the moments after collapse, where the star has exploded and left an empty void in its place, where a new black hole has emerged.

old.png

Hubble snaps images of the birthplace of stars within a cluster: The dust and gas expand within the cluster due to the powerful influence of baby stars. With these new images comes improved detail and a clearer view for astronomers to study how early stars are born and change over time.

baby.png

Hubble image of galaxies colliding: The distorted spirals of two distant galaxies colliding are captured here in a new image from the NASA/ESA Hubble Space Telescope. The typically symmetric spirals common in spiral galaxies appear significantly warped, as the shape of both galaxies is torn apart by their gravitational pulls.

collide.png

Model Details

@misc{weinzierl2023sdhubble1,
  author = {Weinzierl, Maxwell A.},
  title = {Hubble Diffusion v1: Stable Diffusion v1.4 fine tuned on ESA Hubble Deep Space Images & Captions},
  year={2023},
  howpublished= {\url{https://huggingface.co/Supermaxman/hubble-diffusion-1}}
} 

Also, be sure to check out the new and improved Hubble Diffusion v2!

Examples

We recommend using 🤗's Diffusers library to run Hubble Diffusion.

Usage

pip install transformers diffusers accelerate
import torch
from diffusers import StableDiffusionPipeline

model_id = "Supermaxman/hubble-diffusion-1"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
# saves significant GPU memory for small inference cost
pipe.enable_attention_slicing()

prompt = "Hubble snaps images of the birthplace of stars within a cluster: The dust and gas expand within the cluster due to the powerful influence of baby stars. With these new images comes improved detail and a clearer view for astronomers to study how early stars are born and change over time."
image = pipe(prompt).images[0]
image

example.png

Model description

Trained on ESA Hubble Deep Space Images & Captions using Google Colab Pro with a single A100 GPU for around 33,000 steps (about 12 hours, at a cost of about $20).

Links

Trained by Maxwell Weinzierl (@Supermaxman1).

Citation

@misc{weinzierl2023sdhubble1,
  author = {Weinzierl, Maxwell A.},
  title = {Hubble Diffusion v1: Stable Diffusion v1.4 fine tuned on ESA Hubble Deep Space Images & Captions},
  year={2023},
  howpublished= {\url{https://huggingface.co/Supermaxman/hubble-diffusion-1}}
} 
Downloads last month
5
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Supermaxman/hubble-diffusion-1