Text-to-image finetuning - rgres/Seg2Map-finetuned

This pipeline was finetuned from stabilityai/stable-diffusion-2 on the rgres/AerialDreams dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ["Chemin de Saint-Antoine, Saint-Cyr-sur-Mer, Toulon, Var, Provence-Alpes-Cote d'Azur, Frane", 'Aerial view of Rond-Point de la 1e Armee Francaise - Lieutenant Paul Meyer, Mulhouse, Haut-Rhin, Grand Est, France metropolitaine, 68100, France', '31, Rue Molière, SS ace Coeur, Pyramides, La Roche-sur-Yon, Vendee, Pays de la Loire, France metropolitaine, 85000, France', 'Aerial view of Mourenx, Pau, Pyrenees-Atlantiques, Nouvelle-Aquitaine, France metropolitaine, 64150, France', '17 rue du moutier, Angousrine-Vileneuve-Les-Escaldes, Pyrenees Orientales, Occitanie, France metropolitaine, 66760, France']:

val_imgs_grid

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("rgres/Seg2Map-finetuned", torch_dtype=torch.float16)
prompt = "Chemin de Saint-Antoine, Saint-Cyr-sur-Mer, Toulon, Var, Provence-Alpes-Cote d'Azur, Frane"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

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

More information on all the CLI arguments and the environment are available on your wandb run page.

Downloads last month
9
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.

Model tree for rgres/satellite_diffusion

Finetuned
(141)
this model

Dataset used to train rgres/satellite_diffusion