Both ai-toolkit and OneTrainer can train FLUX.2 dev LoRAs. Here is how they compare, using each project's docs and GitHub activity.
| ai-toolkit | OneTrainer | |
|---|---|---|
| FLUX.2 dev support | supported (reference) | supported |
| GitHub stars | 12321 | 3243 |
| Last commit | 2026-10-16 | 2026-10-16 |
| Latest release | none published | none published |
| VRAM (FLUX.2 dev) | 80 GB recommended; ai-toolkit ships train_lora_flux_24gb.yaml | |
| Overview | Ostris' trainer with a web UI and YAML configs; widest day-0 support for new image models. Community threads call it the easiest option for Flux/Krea. | GUI + CLI trainer with a broad model list; users report good VRAM use and speed but more settings to configure. |
If you want the quickest start with a web UI, ai-toolkit is the usual community pick; choose a script-based trainer if you already use its ecosystem. We don't have a sourced head-to-head quality benchmark for FLUX.2 dev between these two, so treat any "better results" claim as unknown.
Cheapest 24 GB+ cards (2026-10-16 14:43 UTC) from RunPod and Vast.ai. Prices move constantly; see the live price table.
| GPU | VRAM | RunPod community $/hr | Vast.ai cheapest $/hr |
|---|---|---|---|
| RTX 3090 | 24 GB | $0.22 | $0.12 |
| RTX A5000 | 24 GB | $0.16 | — |
| RTX PRO 4000 | 24 GB | $0.50 | $0.26 |
| RTX 3090 Ti | 24 GB | $0.27 | — |
| RTX A6000 | 48 GB | $0.33 | — |
| RTX 4090 | 24 GB | $0.34 | $0.39 |
Both support it. There is no sourced quality benchmark between them for this model yet; pick based on workflow (UI vs scripts) and the notes above.
supported (reference)
supported
Data updated 2026-10-16. Disclosure: RunPod and Vast.ai links are referral links; ImageLoRA may earn a commission at no cost to you. unknown = not yet verified from a source.