Diffusion Explorer: interactive visualizations of diffusion and flow models (1.2k stars)
alec_helbling · x · 2026-09-08
Diffusion Explorer is an open-source interactive educational tool (1.2k GitHub stars) for visualizing the geometric intuition behind diffusion and flow-based generative models. It implements training objectives like Flow Matching and Denoising Score Matching, shows sample dynamics over time and across training, supports training on custom hand-drawn distributions, and includes an interactive Rectified Flow explainer.
More from Research
- DeepMind's AlphaGenome Atlas predicts impact of all 9 billion possible DNA letter changes — Google DeepMind · 2026-09-08
- Study of 26,811 Chinese Students: AI Boosts Homework Scores 18% but Cuts Exam Results 20% — soumitrashukla9 · 2026-09-08
- LeVJEPA matches V-JEPA 2 with up to 20x less pretraining compute, no heuristics — Cohere_Labs · 2026-09-08
- McGill txtlab releases 149K plot summaries and crowd-sourced narrative datasets — _akpiper · 2026-09-08
- Most recurring multilingual SAE features fail causal validation — only one truly drives translation in Gemma — ravithejads · 2026-09-08
- Spectrogram-to-Sound AI Meets Bioacoustics for Deeper Bird Vocalization Research — CatAstro_Piyush · 2026-09-08