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

Implementation of Taming Transformers for High-Resolution Image Synthesis (https://arxiv.org/abs/2012.09841) in PyTorch

Text-to-Image Synthesis using Multimodal (VQGAN + CLIP) Architectures

Gradio Web app for running VQGAN-CLIP locally

VQGAN from LDM without hell of dependencies

Text-to-Image Multimodal Generator which generate images from text-prompts inputs