stable-diffusion-space-hubble-images

<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. -->

Text-to-image finetuning - AIStrong/stable-diffusion-space-hubble-images

This pipeline was finetuned from stable-diffusion-v1-5/stable-diffusion-v1-5 on the Supermaxman/esa-hubble dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Hubble image of a colorful ringed nebula: a new vibrant ring-shaped nebula was imaged by the NASA/ESA Hubble Space Telescope.', 'Pink-tinted plumes in the Large Magellanic Cloud: The aggressively pink plumes seen in this image are extremely uncommon, with purple-tinted currents and nebulous strands reaching out into the surrounding space.']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("AIStrong/stable-diffusion-space-hubble-images", torch_dtype=torch.float16)
prompt = "Hubble image of a colorful ringed nebula:  a new vibrant ring-shaped nebula was imaged by the  NASA/ESA Hubble Space Telescope."
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 30
• Learning rate: 1e-05
• Batch size: 1
• Gradient accumulation steps: 4
• Image resolution: 512
• Mixed-precision: fp16