import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ShinnosukeU/kanji_vae_decoder_only", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Text-to-image finetuning - ShinnosukeU/kanji_vae_decoder_only
This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the ShinnosukeU/kanji_diffusion_dataset dataset. Below are some example images generated with the finetuned pipeline using the following prompts: Nothing:
Training info
These are the key hyperparameters used during training:
- Epochs: 100
- Learning rate: 1.2e-06
- Batch size: 2
- Gradient accumulation steps: 4
- Image resolution: 128
- Mixed-precision: None
More information on all the CLI arguments and the environment are available on your wandb run page.
- Downloads last month
- -
Model tree for ShinnosukeU/kanji_vae_decoder_only
Base model
CompVis/stable-diffusion-v1-4