A latent text-to-image diffusion model capable of generating photo-realistic images given any text input

Uses pixray to generate an image from text prompt

Stable Diffusion on Danbooru images

Fast, minimal port of DALL·E Mini to PyTorch

Generate a logo using text.

Animating prompts with stable diffusion

Generate a painting using text.

Feed forward VQGAN-CLIP model

Detailed, higher-resolution images from Stable Diffusion

Generate images using a variety of techniques - Powered by Discoart

Generate images from a text prompt

A 1.4B parameter text2im model from CompVis, finetuned on CLIP text embeds and curated data.

Generate 768px images from text using CompVis `retrieval-augmented-diffusion`

stable-diffusion with v1-5 checkpoint

Text-to-video generation

Instance-Conditioned GAN

VQ-Diffusion for Text-to-Image Synthesis

Generate Pokemons with Projected GAN

GLIDE-text2im w/ humans and experimental style prompts.

Generate images from text using CLIP guided latent diffusion

Archer on Stable Diffusion via Dreambooth

CLIP Guided latent k-diffusion

stylegan3 + clip

Generates pokemon sprites from prompt

Synthesize drawings to match a text prompt

Styledreams -- CLIP x Stylegan2

text-to-image with latent diffusion

Generate images quickly with GLID-3 (non-xl)

Generate retro videogame art using text.

Training-Free Text-to-Image Generation

stable-diffusion-textual-inversion fine-tuned with ugly sonic

Styled text-to-drawing synthesis method.

text-to-image generation

Text-to-image synthesis using contrastive learning

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

Composable Diffusion

Monkey Island database for Retrieval-augmented Diffusion model