Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
stable-diffusion-xl
stable-diffusion-xl-diffusers
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kopyl/miniSDXL", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Motivation: SDXL is a great model, especially for fine-tuning, but fine-tuning on SDXL's standard size is expensive, so i made a model which can generate images of 256x256px size. It allows faster and cheaper training experimentation and can improve a creative process through much faster inference time.
Huuuuge thanks to Microsoft for providing GPU for training ❤️
Trained on LAION Improved Aesthetics 6plus.
Want to collaborate on open source together with me? Send me a message: kopyloleh@gmail.com / telegram @kopyl
Check my other cool projects:
- Logo generator
- Icon generator
- I'm a contributor to A1111, PixArt-alpha, Onediff
- More
Check some cool images i was able to generate with this model.
- Downloads last month
- 4
Model tree for kopyl/miniSDXL
Base model
stabilityai/stable-diffusion-xl-base-1.0