Nerogar/OneTrainer
Source: https://github.com/nerogar/onetrainer
README references StableTuner as defunct (archived); that is a different project.
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "GUI and CLI trainer for full fine-tune, LoRA and embeddings across many diffusion models with masked training, aspect-ratio bucketing and EMA; an alternative to kohya-based stacks.",
"source_type": "repository",
"availability": "available",
"next_check_at": "2026-10-18T00:00:00.000Z",
"upstream_updated_at": "2026-10-16T18:14:06.000Z"
}Evidence claims
- [upstream_claim] README: 'one-stop solution for all your Diffusion training needs' with GUI and CLI; training methods full fine-tune, LoRA, embeddings; supports SD 1.5/2.x/3.x/SDXL, FLUX.1, Flux.2, Chroma, Qwen Image, Z-Image, Sana, PixArt, Hunyuan Video and others. source
- [upstream_claim] README requires Python >=3.10 and <3.14; gives no VRAM figures. source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | AGPL-3.0 | restricted | restricted | restricted | unknown | Repository lists AGPL-3.0; copyleft obligations not analysed. |
| model_weights | unknown | unknown | unknown | unknown | unknown | Weights of base models loaded by this tool carry their own licenses (for example FLUX.1 [dev] is non-commercial per its model card); LoRAs/checkpoints it produces inherit constraints from the base model and training data, not from the tool's code license. Not assessed here. |