bilingual language model based on General Language Model (GLM) framework

Clip-Guided Diffusion Model for Image Generation

Generates pokemon sprites from prompt

Real-ESRGAN super-resolution model from ruDALL-E

face alignment using stylegan-encoding

Image Manipulatinon with Diffusion Autoencoders

Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Global Tracking Transformers

Colorization using a Generative Color Prior for Natural Images

Language-Free Training of a Text-to-Image Generator with CLIP

Composable Diffusion

Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN

VQ-Diffusion for Text-to-Image Synthesis

text-to-image generation

Panoptic Scene Graph Generation

text-to-image with latent diffusion

Unsupervised Night Image Enhancement

Inpainting using Denoising Diffusion Probabilistic Models

stable-diffusion with negative prompts, more scheduler

Pose-Invariant Hairstyle Transfer

End-to-End Document Image Enhancement Transformer