gremlin97/RemoteDiff

1 2---3license: creativeml-openrail-m4base_model: runwayml/stable-diffusion-v1-55datasets:6- None7tags:8- stable-diffusion9- stable-diffusion-diffusers10- text-to-image11- diffusers12inference: true13---14    15# Text-to-image finetuning - gremlin97/RemoteDiff16 17This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **None** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A satellite image of a crop field']: 18 19![val_imgs_grid](./val_imgs_grid.png)20 21 22## Pipeline usage23 24You can use the pipeline like so:25 26```python27from diffusers import DiffusionPipeline28import torch29 30pipeline = DiffusionPipeline.from_pretrained("gremlin97/RemoteDiff", torch_dtype=torch.float16)31prompt = "A satellite image of a crop field"32image = pipeline(prompt).images[0]33image.save("my_image.png")34```35 36## Training info37 38These are the key hyperparameters used during training:39 40* Epochs: 541* Learning rate: 1e-0642* Batch size: 443* Gradient accumulation steps: 444* Image resolution: 22445* Mixed-precision: fp1646 47 48More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/gremlin/text2image-fine-tune/runs/tegl1gtv).49