pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("dineth554/PIXELFORGE_INPAINT", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]PIXELFORGE_INPAINT_BETA
Model Description
PIXELFORGE_INPAINT_BETA is an advanced image inpainting model optimized for high-quality content completion tasks. Utilizing the Diffusor approach, this model excels in generating coherent and contextually relevant content to fill in missing or damaged parts of an image. It is particularly suitable for digital art restoration, content creation, and sophisticated image manipulation applications.
Model Details
- Model Type: Inpainting
- Parameters: 1.5 billion
- File Size: 12 GB (combined from two safetensor files)
- License: MIT License
- Dataset: Trained on a diverse dataset including landscapes, portraits, and abstract art.
Intended Use
This model is designed for:
- Image inpainting and restoration
- Creative art generation
- Removing unwanted elements or filling missing parts of images
Installation
To use the PIXELFORGE_INPAINT_BETA model, ensure you have the following dependencies installed:
pip install torch transformers diffusers
- Downloads last month
- -
# Gated model: Login with a HF token with gated access permission hf auth login