Models that generate images from text prompts
Uses pixray to generate an image from text prompt
Feed forward VQGAN-CLIP model
Instance-Conditioned GAN
A 1.4B parameter text2im model from CompVis, finetuned on CLIP text embeds and curated data.
Generate Pokemons with Projected GAN
GLIDE-text2im w/ humans and experimental style prompts.
stylegan3 + clip
Generates pokemon sprites from prompt
Synthesize drawings to match a text prompt
Training-Free Text-to-Image Generation
Generate a logo using text.
Styledreams -- CLIP x Stylegan2
Text-to-image synthesis using contrastive learning
Styled text-to-drawing synthesis method.