StyleCLIP
Image manipulator
This project provides an implementation of a method to manipulate images by driving the style with text.
Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)
4k stars
74 watching
560 forks
Language: HTML
last commit: over 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 eladrich/pixel2style2pixel | An implementation of an image-to-image translation framework using StyleGAN encoders and generators. | 3,196 |
 openai/clip | A neural network trained on image and text pairs to predict the most relevant text snippet given an image | 26,061 |
 jcjohnson/neural-style | An algorithm to combine the content of one image with the style of another, using convolutional neural networks. | 18,310 |
 nvlabs/stylegan2 | Improves upon the state-of-the-art architecture for generating high-quality images using a GAN-based approach | 10,996 |
| nvlabs/stylegan | A deep learning framework implementing a generator architecture for generating images with controllable attributes and disentangled latent factors | 14,157 |
 ofa-sys/ofa | Develops a unified sequence-to-sequence learning framework to unify modalities and tasks through pretraining and fine-tuning | 2,419 |
 lengstrom/fast-style-transfer | An implementation of fast style transfer using TensorFlow and neural networks to apply artistic styles to images and videos. | 10,927 |
 clovaai/stargan-v2 | A Python implementation of an image-to-image translation model for generating diverse images across multiple domains. | 3,506 |
 junyanz/igan | Interactive image generation using Generative Adversarial Networks to satisfy user edits in real-time | 3,977 |
 rinongal/textual_inversion | A method to guide text-to-image generation using images and natural language | 2,930 |
 cysmith/neural-style-tf | An implementation of image style transfer using convolutional neural networks in TensorFlow. | 3,104 |
 rameenabdal/clip2stylegan | Automatically extracts and labels edit directions from StyleGAN images using CLIP pre-trained latent spaces | 86 |
 ai-forever/kandinsky-2 | A multilingual text2image latent diffusion model with improved aesthetics and controllability | 2,769 |
| nvlabs/stylegan3 | An implementation of a generative adversarial network architecture designed to improve image synthesis and video generation capabilities | 6,447 |
 jina-ai/dalle-flow | An interactive workflow for generating high-definition images from text prompts using a human-in-the-loop approach | 2,834 |