# GLIDE Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/glide
> Markdown URL: https://aitinkerers.org/technologies/glide.md
> Technology record last updated: 2026-03-08T18:16:11Z
> Generated: 2026-09-23T08:56:46Z

OpenAI's diffusion model for photorealistic image synthesis and local editing via text prompts.

GLIDE (Guided Language-to-Image Diffusion for Generation and Editing) scales a 3.5 billion parameter diffusion model to outperform GANs and DALL-E in human preference benchmarks. It utilizes classifier-free guidance to maintain high spatial fidelity while adhering strictly to complex text descriptions. Beyond base generation, the architecture supports zero-shot image inpainting, allowing users to modify existing photos (changing a dog's breed or adding a sunset) by masking regions and providing natural language instructions. The model demonstrates that diffusion techniques offer superior photorealism and fine-grained control for professional creative workflows.

- Official technology site: https://github.com/openai/glide-text2im
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [x2 faster diffusion model in 3 lines of code](https://paris.aitinkerers.org/talks/rsvp_gDKrDrEbvwU)

In a few lines of code, pruna enables you to compress any text to image GenAI model. We will show how we can easily generate an image, and how we can speedup this generation without any quality loss.

- Event context: AI Tinkerers - Paris Meetup on January 30th — 2025-01-30 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_gDKrDrEbvwU

### [Training Diffusion Transformers for Style Transfer (for the GPU poor)](https://la.aitinkerers.org/talks/rsvp_z4k8pNn_y6w)

We trained diffusion transformers to generate images from text in the style of the Simpsons and Legos on a single commodity GPU.

- Event context: May 21st - LA AI Tinkerers Meetup & Demos — 2024-05-22 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_z4k8pNn_y6w

## Related Technologies

- [DALL-E 2](https://aitinkerers.org/technologies/dall-e-2) ([Markdown](https://aitinkerers.org/technologies/dall-e-2.md)) — 7 public demos
- [DALL-E 3](https://aitinkerers.org/technologies/dall-e-3) ([Markdown](https://aitinkerers.org/technologies/dall-e-3.md)) — 12 public demos
- [Imagen](https://aitinkerers.org/technologies/imagen) ([Markdown](https://aitinkerers.org/technologies/imagen.md)) — 10 public demos
- [Midjourney](https://aitinkerers.org/technologies/midjourney) ([Markdown](https://aitinkerers.org/technologies/midjourney.md)) — 14 public demos
- [Stable Diffusion](https://aitinkerers.org/technologies/stable-diffusion) ([Markdown](https://aitinkerers.org/technologies/stable-diffusion.md)) — 32 public demos
- [Diffusion model](https://aitinkerers.org/technologies/diffusion-model) ([Markdown](https://aitinkerers.org/technologies/diffusion-model.md)) — 3 public demos
- [Generative AI](https://aitinkerers.org/technologies/generative-ai) ([Markdown](https://aitinkerers.org/technologies/generative-ai.md)) — 45 public demos
- [GPU](https://aitinkerers.org/technologies/gpu) ([Markdown](https://aitinkerers.org/technologies/gpu.md)) — 12 public demos
- [Pruna](https://aitinkerers.org/technologies/pruna) ([Markdown](https://aitinkerers.org/technologies/pruna.md)) — 1 public demo
- [Self-hosted AI](https://aitinkerers.org/technologies/self-hosted-ai) ([Markdown](https://aitinkerers.org/technologies/self-hosted-ai.md)) — 1 public demo
- [Style Transfer](https://aitinkerers.org/technologies/style-transfer) ([Markdown](https://aitinkerers.org/technologies/style-transfer.md)) — 1 public demo
- [Transformer](https://aitinkerers.org/technologies/transformer) ([Markdown](https://aitinkerers.org/technologies/transformer.md)) — 11 public demos