← ImageLoRA
How to train an SDXL LoRA
Which trainers support SDXL, how much VRAM you need, and settings that work. Every row links to its source.
Trainer support
| Trainer | Status |
|---|
| ai-toolkit | supported |
| OneTrainer | supported |
| musubi-tuner | not listed |
| kohya sd-scripts | supported |
| SimpleTuner | supported |
VRAM
low-VRAM friendly with gradient checkpointing, 8-bit optimizer, cached latents (exact GB unknown)
Known-good settings
- Gradient checkpointing
- 8-bit optimizer
- Cache latents
- OneTrainer: 'compile' + int8 quant on RTX 20xx+
General tips
- Gated Hugging Face models: click 'Agree and access' on each model page, or you'll get 403 errors
- Steps scale with dataset size (steps = epochs x images at batch 1)
- A safe start: LoKr with auto rank (~64), batch/grad accumulation 4
- Leave out of your captions whatever you want burned into the LoRA; caption what should stay changeable
- ai-toolkit dataset folder weights let you train the same images with long, medium and short captions in separate folders
- ai-toolkit supports validation loss, which shows when a run stops improving
- In ai-toolkit, Cache text embeddings works for basically every model and frees the text encoder from VRAM and RAM
- Prefer int8 convrot over qfloat8 quantization in ai-toolkit: better quality at the same memory
- Gradient accumulation and batch size don't scale the learning rate in ai-toolkit; a bigger batch needs about 1.5-2.5x the steps
Where to rent a GPU
See cheapest GPU to train a LoRA (RunPod, Vast.ai).
Sources
Weekly newsletter: new models, trainer releases, cheapest GPUs.
Subscribe
Data updated 2026-10-20. RunPod and Vast.ai links are referral links. unknown = no data yet. · Raw data (JSON) · llms.txt