# inclusionAI/IDM

> Official code for Intrinsic Distribution Matching (IDM), a distillation method that speeds up text-to-image diffusion models to 1-2 sampling steps by matching feature moments in the generator's own EMA space, without an external encoder.

- Magnitude: 3.6 out of 10 — Early signal
- Stars: 177 total · +6 stars measured 2026-11-02, 08:35–10:54 UTC, ≈ 26 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · License: Apache-2.0 · Created: 2026-10-29 · Last push: 2026-10-30
- GitHub: https://github.com/inclusionAI/IDM · Homepage: https://www.inclusion-ai.org/IDM/ · Page: https://gitnova.dev/en/r/inclusionAI/IDM

## Useful for

- Distill a text-to-image diffusion model to 1-2 NFE for fast inference
- Reproduce the paper's long-text rendering and GenEval benchmarks
- Train a LoRA adapter to speed up a large image model with minimal quality loss

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 08:35–10:54: 171 → 177 stars (+6). This is the change over that interval.
- Estimated end-of-day forecast: about +26 stars, using observed gains and the previous day.
- The repository is 4 days old and already has 177 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #147.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 5
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 39 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 3

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-29 … 2026-11-02: 2, 56, 54, 58, 6

## Spotted in now

- Top new repositories this week: #147

## More in this category

1. **mromidev/claude-animated-shorts** — 6.7 · Early signal · Generative media · TypeScript · +119 stars measured 2026-11-02, 02:55–10:51 UTC, ≈ 260 by evening
   A free Claude skill that produces 55-70 second vertical animated story shorts with 2D characters in a 3D world, rendered locally via three.js inside Remotion without an AI video generator.
   Full card: https://gitnova.dev/en/r/mromidev/claude-animated-shorts.md
2. **hyz317/HairDeck** — 6.5 · Early signal · Generative media · Python · +109 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 245 by evening
   HairDeck generates stylized hair cards and the spring-bone chains that animate them from a single image, exporting results as GLB or VRM. A research project for 3D artists and avatar developers.
   Full card: https://gitnova.dev/en/r/hyz317/HairDeck.md
3. **andreavolpato/spektrafilm** — 6.2 · Breakout · Generative media · Python · +138 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 274 by evening
   Reference Python implementation of physically based spectral simulation of analog photography: from a RAW image through virtual negative, print, and scan using film and paper datasheet data.
   Full card: https://gitnova.dev/en/r/andreavolpato/spektrafilm.md
4. **anhao/ai-pose-gallery-zh** — 5.9 · Cooling · Generative media · TypeScript · +242 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 500 by evening
   Chinese localization of an AI pose reference gallery: 1439 records and 2878 images with a ready-to-deploy dependency-free static site. Useful for artists and 3D modelers picking poses.
   Full card: https://gitnova.dev/en/r/anhao/ai-pose-gallery-zh.md
5. **D3voz/openjutsu** — 5.8 · Early signal · Generative media · TypeScript · +96 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 221 by evening
   A local web app for swapping characters and objects in videos: drop a video and a character photo, and the main person in the frame is replaced by your character while camera, cuts and soundtrack stay intact. Runs on your own GPU via…
   Full card: https://gitnova.dev/en/r/D3voz/openjutsu.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 11:06 UTC, updated every 30 minutes.