# KohakuBlueleaf/KohakuMossTrainer

> A finetuning framework for MOSS-Image: every LyCORIS algorithm and full finetune on text-image data at native resolutions, plus inference, on Windows and Linux from 6 GB cards to multi-GPU nodes.

- Magnitude: 1.0 out of 10 — Cooling
- Stars: 119 total · +0 stars measured 2026-10-24, 00:03–01:32 UTC, ≈ 4 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2026-10-18 · Last push: 2026-10-20
- GitHub: https://github.com/KohakuBlueleaf/KohakuMossTrainer · Page: https://gitnova.dev/en/r/KohakuBlueleaf/KohakuMossTrainer

## Useful for

- Train a style LoRA for MOSS-Image on a local image folder on a single RTX 4090
- Run a full MOSS-Image finetune on one 24 GB card with host optimizer states
- Export a trained adapter in ComfyUI format and load it with a LoRA loader node

## Why it’s here

- Star-counter measurements on 2026-10-24 (UTC), 00:03–01:32: 119 → 119 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +4 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 119 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #188.

## 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: 8
- Issues and pull requests: 3
- Watchers: 1
- Average over the last week: 18 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0
- Latest release: v0.1.0 (2026-10-18)

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-18 … 2026-10-24: 59, 25, 13, 7, 10, 5, 0

## Spotted in now

- Top new repositories this week: #188

## Similar by description

1. **deepseek-ai/DeepSpec** — 0.8 · Steady · Language models · Python · +0 stars measured 2026-10-24, 00:11–01:33 UTC, ≈ 2 by evening
   Full-stack pipeline for training and evaluating draft models for speculative decoding: data preparation, training against a target-model cache, and acceptance measurement on benchmarks. Supports DSpark, DFlash and Eagle3.
   Full card: https://gitnova.dev/en/r/deepseek-ai/DeepSpec.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 2026-10-24 01:35 UTC, updated every 30 minutes.