5 phút đọc
shootthesound/Fizgig: Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & – Repository shootthesound/Fizgig. Mô tả: Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune, profile, repair and extract LoRAs & LoKR for Image, Video & Music Models. 525 stars, 53 forks, ngôn ngữ chính Python, cập nhật 2026-10-15.
1. Repository làm gì?
Fine-tune base models on consumer GPUs — down to 8 GB. Fix broken LoRAs without retraining. Find the best epoch by eye. A train · fine-tune · repair · explore workbench built end-to-end for Flux 2 Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Z-Image Turbo, SDXL and Anima — training on photos, video, sound and voices, from quick LoRAs to the full base model.
No GPU, or want a bigger one? Fizgig runs on rented hardware — one click, nothing to install. Deploying through that link supports Fizgig's development at no extra cost to you.
Start-to-finish walkthrough — install, prep, caption, train, and the workbench tools
A trainer and workbench for image, video and music models, in its own window on your computer, in your browser, or on a rented GPU — and you can watch a run from your phone. Every trainer makes LoRAs; Fizgig is also built around what you do with them afterwards:
Memory plans itself: precision, block swap and previews size to your free VRAM, and if a preview can't fit, training keeps going. Fizgig loads kohya, PEFT, OneTrainer, AI-Toolkit and LyCORIS LoRAs, and saves .safetensors that drop straight into ComfyUI. Free and open source.
The Fizgig 8 tour · watch it on YouTube
2. Dữ liệu và cấu trúc đáng chú ý
Every image and video model gets all four workbench tools; ACE-Step has Studio and Extract. Qwen Image 2.1 trains on the base model and previews on Qwen's own Turbo (8 steps, CFG 1); your LoRAs work on both. MiniMax H3 also makes RefMods, tuned against H3 itself rather than a plain encode (how do I…?). Fizgig's training adapters for Qwen Image 2.1 and Z-Image Turbo are free on Hugging Face for any trainer. Full fine-tuning has its own guide.
Each tool works on your own runs or any LoRA you've downloaded, and they hand off to each other. More detail.
Full list: docs/TRAINING.md. Everything also runs headless: docs/CLI.md.
Needs an NVIDIA RTX 30/40/50-series or an AMD Radeon with ROCm, Windows 10/11 or Linux, Python 3.10–3.13, and 32 GB of system RAM recommended. Full requirements, AMD ROCm and model downloads: docs/INSTALL.md.
Clone the repo rather than downloading the ZIP (the updater pulls with git):
Model files download from the Preferences tab: one Download models for me button per model.
The whole app runs in a browser tab on RunPod, with a drag-and-drop file manager for big datasets and fine-tunes (the File manager button in the sidebar), one-click model downloads and an optional auto-stop when training finishes. ⚡ Deploy on RunPod → · Guide
3. Khả năng ứng dụng và giới hạn
Mid-job on the old pod with the remote desktop? It stays available as Fizgig Classic v7.x, and pods you already have keep running as they are.
Work down through the numbered tabs:
Tip: give one sample prompt something your dataset doesn't have, such as a specific pose, angle or setting that none of your photos show (for example "looking over her shoulder from a low angle" when your photos are all straight-on portraits). Early epochs follow it. When a LoRA starts to overtrain, that is the first thing to fail: the previews drift back to your dataset's framing even though the prompt asks for something else. The last epoch that still follows it is a good one to keep.
The unnumbered tabs are Runs & outputs, the workbench (Profiler, Studio, LoRA Royale, RefMod Toolkit, Extract, Metadata), Preferences, and Pods. The video tutorial walks through all of it.
Run update_fizgig.bat as always. Fizgig 7's desktop app is replaced by the new one: start it with Launch Fizgig.bat from now on (run_fizgig.bat is gone, so point a shortcut at the new file). Everything of yours moves into one user_data folder: your settings, presets, models, cache and queued runs come across, Fizgig opens on the model you last trained, and the welcome on the first start shows where everything went.
Community translation: Korean (한국어) by @ssain3d-lgtm, an unofficial add-on that translates the UI at runtime without touching Fizgig's files and uninstalls with one script. If you hit a bug with it installed, uninstall and reproduce before reporting here; translation issues go to its repo.
Fizgig is free. If it saves you time or makes your LoRAs better, a coffee or a GitHub sponsorship keeps it going:
Renting through the RunPod link supports development too, at no extra cost to you.
Fizgig is open source under the Apache License 2.0 — free to use, modify, and redistribute, including commercially, with attribution and no warranty. Third-party components under compatible permissive licenses (and other terms where noted) are listed in THIRD_PARTY_NOTICES.md.
Số liệu repository có thể thay đổi; nên mở liên kết nguồn để kiểm tra README, giấy phép và trạng thái phát hành.
Nguồn tham khảo: Xem bài gốc
