GLIDE-text2im w/ humans and experimental style prompts.
GLIDE finetuned on LAION5B, then more on curated datasets.
GLIDE from OpenAI finetuned on roughly 30M more samples. See `laionide-v3` for the latest.
The predecessor to DALLE-2, GLIDE (filtered) with faster PRK/PLMS sampling.
Generate images from text quickly. See https://replicate.com/afiaka87/laionide-v2 for a new checkpoint.
Guide a StyleGAN3 trained on pictures of mannequins with CLIP.
Generate image from text by guiding a denoising diffusion model. Inference is somewhat slow.