README.md

metadata

base_model: runwayml/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - controlnet
  - diffusers-training
inference: true

controlnet-Jieya/model_out_canny

These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.

prompt: gothic fractals prompt: gothic fractals prompt: gothic fractals

Intended uses & limitations

How to use

from datasets import Dataset
from pathlib import Path
from PIL import Image

face_image = Path("images/original")
canny_image = Path("images/canny_images")

def entry_for_id(entry_id):
    if type(entry_id) == int:
        entry_id = f"{entry_id:05}"
    image = Image.open(face_image/f"fractal_{entry_id}.jpg")
    image_cond = Image.open(canny_image/f"canny_fractal_{entry_id}.jpg")
    caption = "gothic fractals"
    return {
        "image": image,
        "canny_images": image_cond,
        "caption": caption,
    }


def generate_entries():
    for x in range(1, 6463):  # Start from 1 and go up to 6462
        yield entry_for_id(x)

ds = Dataset.from_generator(generate_entries)
ds.push_to_hub('Jieya/fractal_image_6462')

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]