Luo-Yihong/VA-TDM

VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation

Python

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast Luo-Yihong/VA-TDM is gaining stars, and where it lands on Trendshift and GitHub Trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Nov 4 – Nov 6, 2026

Stars +41 in 3 days

Forks +0 in 3 days

Merged PRs 0 in 3 days

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Nov 4Nov 5Nov 6

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained
Wed, Nov 4, 2026	+0	+0
Thu, Nov 5, 2026	+41	+0
Fri, Nov 6, 2026	+0	+0
Total	+41	+0

Recent discussions about this repository across the web

Nov 61 post
- on SD3.5-Medium, 4-step GenEval goes 0.61 (TDM) to 0.67, matching the 50-step teacher at CFG 7. on FLUX.2-Klein 4B, OCR goes 0.64 to 0.69 over the released 4-step model
  Read full on X, posted by @FooSteins
  @FooSteins · x.com
Nov 51 post
- VA-TDM’s released code trains a four-step SD3.5-Medium LoRA. The paper reports a 61.33% preference win rate over Fast-H3 on MiniMax-H3, from 10 prompts. That 33B video result is not the released…
  Read full on X, posted by @burnrate_ai
  @burnrate_ai · x.com