Text-to-image finetuning - linhqyy/sd-pokemon-15k-model

This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the lambdalabs/pokemon-blip-captions dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['cute hippo']:

val_imgs_grid

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("linhqyy/sd-pokemon-15k-model", torch_dtype=torch.float16)
prompt = "cute hippo"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

  • Epochs: 72
  • 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
7
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 linhqyy/sd-pokemon-15k-cp-model

Finetuned
(987)
this model

Dataset used to train linhqyy/sd-pokemon-15k-cp-model