IC-Light
Image Relighter
An image relighting model that generates images with consistent lighting conditions given text prompts.
More relighting!
6k stars
56 watching
363 forks
Language: Python
last commit: 28 days ago
Linked from 1 awesome list
amrzv/awesome-colab-notebooksRelated projects:
| Repository | Description | Stars |
|---|---|---|
 tothebeginning/pulid | A deep learning framework for creating customizable images through contrastive alignment and prompt-following. | 2,664 |
 adamian98/pulse | A software project that uses generative models to improve image resolution through self-supervised learning | 7,939 |
 lightning-ai/pytorch-lightning | A framework for building and training AI models on multiple GPUs or TPUs with minimal code changes. | 28,402 |
 junyanz/interactive-deep-colorization | A system for automatically colorizing black and white images with user interactions. | 2,694 |
 borisdayma/dalle-mini | Generates images from text prompts using a variant of the DALL-E model | 14,751 |
 lightly-ai/lightly | A Python library for self-supervised learning on images using contrastive learning techniques. | 3,176 |
 fluidgroup/brightroom | An image editing framework using Core Image and Metal for iOS development | 3,353 |
 donnyyou/torchcv | A comprehensive PyTorch-based framework for computer vision tasks | 2,250 |
 jlampel/extra_lights | Adds physically based lighting presets to Blender's Add menu | 250 |
| lllyasviel/paints-undo | Provides base models of human drawing behaviors in digital paintings with an aim to better align AI models with human artistic needs. | 3,481 |
 senguptaumd/background-matting | Background removal technique to separate an object from its background in images and videos | 4,784 |
 hkuds/lightrag | A software framework for generating and retrieving information from knowledge graphs using large language models | 8,649 |
 skalskip/make-sense | An online tool for labeling photos using computer vision and deep learning techniques | 3,168 |
 pharmapsychotic/clip-interrogator | A tool for optimizing text prompts to generate images with specific characteristics using CLIP and BLIP models. | 2,706 |
 tencentarc/gfpgan | An algorithm for restoring damaged or obscured faces in images | 35,912 |