Pipeline to create Paper2Fig dataset, a dataset for text-to-image generation from research papers and figures (e.g., diagrams of architectures or methods in fields like Machine Learning or Computer Vision)

Vector-Quantized Generative Adversarial Networks

Branch of the original Project "dome272/VQGAN-pytorch" adding an inference file for the VQGAN (Not for the VQGAN Transformers)

yet another VQGAN-CLIP variation

Pytorch implementation of "Taming transformer for high resolution image synthesis (VQGAN)"

Implementing MaskGIT for image inpainting with PyTorch

Multi-Modal Image Generation for News Stories

[ICLR 2024] DAEFR: Dual Associated Encoder for Face Restoration

VQGAN from LDM without hell of dependencies

OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from VQGAN in CompVis/taming-transformers

Art generation using VQGAN + CLIP using docker containers. A simplified, updated, and expanded upon version of Kevin Costa's work. This project tries to make generating art as easy as possible for anyone with a GPU by providing a simple web UI.

VQ-VAE/GAN implementation in pytorch-lightning

Implementation of Binary Latent Diffusion

Fast and controllable text-to-image model.

Traditional deepdream with VQGAN+CLIP and optical flow. Ready to use in Google Colab.

Docker for VQGAN+CLIP (z+quantize method)

Official Implement of Multi-Stage Multi-Codebook (MSMC) TTS

PyTorch codes for "Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors", ACM MM2022 (Oral)

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

Streamlit Tutorial (ex: stock price dashboard, cartoon-stylegan, vqgan-clip, stylemixing, styleclip, sefa)