Finetuning - aditya11997/kandi2-decoder-3.2

This pipeline was finetuned from kandinsky-community/kandinsky-2-2-decoder on the kbharat7/DogChestXrayDatasetNew dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['photo of dogxraysmall']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = AutoPipelineForText2Image.from_pretrained("aditya11997/kandi2-decoder-3.2", torch_dtype=torch.float16)
prompt = "photo of dogxraysmall"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 43
• Learning rate: 1e-05
• Batch size: 1
• Gradient accumulation steps: 4
• Image resolution: 768
• Mixed-precision: None