smithee77 / glide-text2im

GLIDE: a diffusion-based text-conditional image synthesis model

GLIDE

This is the official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

For details on the pre-trained models in this repository, see the Model Card.

PRK and PLMS sampling methods added by Katherine Crowson. Note that PRK and PLMS skip the first and the last timestep, there is not yet a PLMS optimized analogue of the 'fast27' schedule, and there may be other bugs.

Usage

To install this package, clone this repository and then run:

pip install -e .

For detailed usage examples, see the notebooks directory.

• The text2im notebook shows how to use GLIDE (filtered) with classifier-free guidance to produce images conditioned on text prompts.
• The inpaint notebook shows how to use GLIDE (filtered) to fill in a masked region of an image, conditioned on a text prompt.
• The clip_guided notebook shows how to use GLIDE (filtered) + a filtered noise-aware CLIP model to produce images conditioned on text prompts.