Downloads · 30 days
50
4% of all-time downloads
LinFusion-1-5
Yuanshi/LinFusion-1-5
LinFusion-1-5 is a text-to-image model from Yuanshi. Use it when you need an image from a text prompt. It is set up for diffusers.
This model has been pushed to the Hub using the Diffusers library: - Repo: https://github.com/Huage001/LinFusion - Paper: https://huggingface.co/papers/2409.02097
All-time downloads
1.3K
Public
Parameters
99.2M
496 MB on disk
Likes
15
Public
Repo makeup
Click a slice to open those files.
.safetensors198 MB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- Access
- Public
- Created
- Aug 10, 2024
- Updated
- Sep 10, 2024
- SHA
- e0e7d331
Model card
From the Hugging Face model README
This model has been pushed to the Hub using the Diffusers library:
- Basic Usage of LinFusion:
from diffusers import AutoPipelineForText2Image
import torch
from src.linfusion import LinFusion
from src.tools import seed_everything
sd_repo = "Lykon/dreamshaper-8"
pipeline = AutoPipelineForText2Image.from_pretrained(
sd_repo, torch_dtype=torch.float16, variant="fp16"
).to(torch.device("cuda"))
linfusion = LinFusion.construct_for(pipeline)
seed_everything(123)
image = pipeline(
"An astronaut floating in space. Beautiful view of the stars and the universe in the background."
).images[0]
- Task
- Text-to-Image
- Library
- diffusers
- Created
- Aug 10, 2024
- Updated
- Sep 10, 2024