DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Paper • 2410.18666 • Published • 19
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("shallowdream204/DreamClear", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation (NeurIPS 2024)
This repo is used to host DreamClear's checkpoints.
For more details or tutorials see https://github.com/shallowdream204/DreamClear.
- Downloads last month
- 75
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support