kohya_ss
kohya_ss — open-source image project on GitHub.
MirrorMetrics is an open-source image project by AndyLone22 (AndyLone22/MirrorMetrics on GitHub). It has 62 GitHub stars and 8 forks, is released under the MIT license, and was last updated on GitHub on 21 February 2026.
Visual diagnostics for LoRA training — spot overfitting with face biometrics
Point MirrorMetrics at a trained LoRA and its dataset.
It analyzes samples with InsightFace biometrics.
Charts reveal overfitting and dataset problems.
Adjust settings based on what the metrics show.
Visual signals when a LoRA memorizes.
Spot bad or inconsistent training images.
InsightFace-based identity consistency checks.
Guidance on settings to change.
Charts instead of guesswork.
Free for commercial use with attribution.
Download the source and move into the project folder.
git clone https://github.com/AndyLone22/MirrorMetrics.git
cd MirrorMetricsEvery project documents its own setup; start with install requirements.
cat README.md | head -60Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch commandIt is an open-source project at AndyLone22/MirrorMetrics with 162 forks. Check the repo's contributors and recent commits to see how active maintenance is.
MIT licensed — commercial use allowed with attribution.
It is built for Stable Diffusion LoRAs.
InsightFace analysis runs best with one — check the README.
It diagnoses problems and suggests setting changes; you retrain.
kohya_ss — open-source image project on GitHub.
OneTrainer is a one-stop solution for all your Diffusion training needs.
The ultimate training toolkit for finetuning diffusion models
Privacy-first browser tool for tagging LoRA training datasets — no install
Create LoRA training datasets in the browser — Flux 2, Qwen, Nano Banana
FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, SwarmUI, DeepFake, TTS, Animation, Text To Video, Tut…
The most-starred other Image projects in the LibreAI catalogue — the realistic shortlist if MirrorMetrics is not the right fit.
Stable Diffusion web UI
The node-graph powerhouse for precise, professional AI image and video generation.
High performance self-hosted photo and video management solution
PhotoCraft — a clean-room Photoshop reimplementation in pure Rust: layers, masks, adjustment layers, type, vectors, brushes and real PSD files, offline, MIT / Apache-2.0
Focus on prompting and generating
Nearby Image projects in the catalogue, closest in stars to MirrorMetrics — keep exploring the shelf either side of it.
Free local upscaler — 8K photos and 4K video with Real-ESRGAN, no cloud
Point-and-click AI background removal with Segment Anything and BiRefNet
Mobile-friendly DALL-E image generator built with Node and Express
Add AI interior design and virtual staging to your own apps.
Professional AI interior-design toolkit for ComfyUI.
Browser-only AI interface for UI mockups, covers, logos and social images
Free and open — grab the source, star the repo, and start creating.