Text-to-image finetuning - ekshat/Stable_Diffussion_Anime_Style

This pipeline was finetuned from ekshat/stable-diffusion-anime-style on the lambdalabs/naruto-blip-captions dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A person with blue eyes.']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("ekshat/Stable_Diffussion_Anime_Style", torch_dtype=torch.float16)
pipeline = pipeline.to("cuda")

prompt = "A person with blue eyes."
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 17
• Learning rate: 2e-06
• Batch size: 2
• Gradient accumulation steps: 1
• Image resolution: 512
• Mixed-precision: fp16