zjysteven/controlnet_tile
Workable training script for ControlNet tile
This project helps machine learning engineers fine-tune a ControlNet model specifically for image upsampling. You provide a dataset of low-resolution images paired with their high-resolution counterparts, and the script trains a ControlNet model to generate high-resolution images conditioned on low-resolution inputs. The resulting model can then be used to upscale images effectively.
No commits in the last 6 months.
Use this if you need to train a ControlNet Tile model for image upsampling using WebDataset for efficient data loading.
Not ideal if you prefer to use Hugging Face style datasets or are looking for an inference-only solution.
Stars
35
Forks
2
Language
Python
License
—
Category
Last pushed
May 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zjysteven/controlnet_tile"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hnsywangxin/controlnet_stable_tensorrt
stable diffusion, controlnet, tensorrt, accelerate
a-lgil/pose-depot
A collection of ControlNet poses
city96/SD-Latent-Upscaler
Upscaling stable diffusion latents using a small neural network.
camenduru/ControlNet-v1-1-nightly-colab
controlnet v1.1 colab
360CVGroup/RelaCtrl
Efficient controlnet for DiTs