afiaka87 / clip-guided-diffusion

Generate image from text by guiding a denoising diffusion model. Inference is somewhat slow.

afiaka87 / pyglide

The predecessor to DALLE-2, GLIDE (filtered) with faster PRK/PLMS sampling.

afiaka87 / sd-aesthetic-guidance

Use stable diffusion and aesthetic CLIP embeddings to guide boring outputs to be more aesthetically pleasing.

afiaka87 / retrieval-augmented-diffusion

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

afiaka87 / glid-3-xl

CompVis `latent-diffusion text2im` finetuned for inpainting.

afiaka87 / tortoise-tts

Generate speech from text, clone voices from mp3 files. From James Betker AKA "neonbjb".

afiaka87 / ldm-autoedit

afiaka87 / laionide-v4

GLIDE-text2im w/ humans and experimental style prompts.

afiaka87 / mannequin-gan-3-electric-boogaloo-2

Guide a StyleGAN3 trained on pictures of mannequins with CLIP.