Both ai-toolkit and musubi-tuner can train Z-Image LoRAs. Here is how they compare, using each project's docs and GitHub activity.
| ai-toolkit | musubi-tuner | |
|---|---|---|
| Z-Image support | supported (Z-Image, Turbo, De-Turbo) | supported |
| GitHub stars | 12321 | 2098 |
| Last commit | 2026-10-16 | 2026-10-12 |
| Latest release | none published | v0.3.6 |
| VRAM (Z-Image) | Not published. musubi: 12GB+ recommended for image training (general); --fp8_llm saves VRAM | |
| 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. | kohya's CLI scripts for newer models; supports fp8 base weights and recommends 12 GB+ VRAM for image training. |
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 Z-Image between these two, so treat any "better results" claim as unknown.
No verified settings yet.
Cheapest 16 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 A4000 | 16 GB | $0.17 | $0.09 |
| Tesla V100 | 16 GB | $0.19 | $0.10 |
| RTX 3090 | 24 GB | $0.22 | $0.12 |
| RTX 5060 Ti | 16 GB | — | $0.12 |
| RTX 5070 Ti | 16 GB | — | $0.12 |
| RTX A5000 | 24 GB | $0.16 | — |
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 (Z-Image, Turbo, De-Turbo)
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.