Text2All

A comprehensive list of resources about text-guided generative models.

Table of contents

• Works and Papers

  • Text-to-Image
  • Text-to-Video
  • Text-to-3D
  • Text-to-Audio
  • Text-to-Motion
  • Text-to-Style

• Tutorials

  • Resources
  • Blogs and Summaries
  • Videos

Works and Papers

Text-to-Image

• DALL-E - Hierarchical Text-Conditional Image Generation with CLIP Latents

• Imagen - Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

• RE-IMAGEN: Retrieval-augmented Text-to-image Generator

• Stable Diffusion - High-Resolution Image Synthesis with Latent Diffusion Models

• MidJourney

• GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

• Parti - Pathways Autoregressive Text-to-Image

• MagicMix: Semantic Mixing with Diffusion Models

• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

• Imagic: Text-Based Real Image Editing with Diffusion Models

• DIFFEDIT: Diffusion-based Semantic Image Editing With Mask Guidance

• UniTune: Text-Driven Image Editing by Fine Tuning an Image Generation Model on a Single Image

• LAFITE: Towards Language-Free Training for Text-to-Image Generation

• DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

• Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors

• Text2LIVE: Text-Driven Layered Image and Video Editing

• An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

• Prompt-to-Prompt: Latent Diffusion and Stable Diffusion implementation

• StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

• clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIP

• Stable Diffusion Notebooks: Image, Animation, Panorama, text-based real image editing

Text-to-Video

• Make-A-Video: Text-to-Video Generation without Text-Video Data

• Imagen Video: High Definition Video Generation With Diffusion Models

• Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions

• GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

• CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

• NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

Text-to-3D

• DreamFusion: Text-to-3D using 2D Diffusion

• Zero-Shot Text-Guided Object Generation with Dream Fields

• CLIP-Mesh: Generating textured meshes from text using pretrained image-text models

Text-to-Audio

• AudioGen: Textually Guided Audio Generation

• Diffsound: Discrete Diffusion Model for Text-to-sound Generation

Text-to-Motion

• MotionCLIP: Exposing Human Motion Generation to CLIP Space

• Human Motion Diffusion Model

• Language2Pose: Natural Language Grounded Pose Forecasting

Text-to-Style

• Text-Driven Stylization of Video Objects

Tutorials

Resources

• Awesome AI image synthesis - A list of awesome tools, ideas, prompt engineering tools, colabs, models, and helpers for the prompt designer playing with aiArt and image synthesis

• Tools and Resources for AI Art

• DiffusionDB - large-scale text-to-image prompt dataset (it contains 2 million images)

Blogs and Summaries

• The Illustrated Stable Diffusion

• Introduction to Diffusion Models

• How DALL-E works

• How Imagen works

• Build Your Own Imagen

Videos

• Diffusion models from scratch in PyTorch

• Yannic Kilcher - Text-to-Image models are taking over! (Imagen, DALL-E 2, Midjourney, CogView 2 & more)

• Yannic Kilcher - Stable Diffusion Takes Over!