Run on Badgr

LoRA Training

Fine-tune LoRA adapters on open models with cost-capped training jobs, checkpoint logs, and automatic teardown when training completes.

Start LoRA training Get help running this

Specific LoRA Training jobs

Train a Flux LoRA

Fine-tune a LoRA adapter on Flux.1 from a small image set — for a style, subject, or product look you want Flux to reproduce consistently.

Train an SDXL LoRA

Fine-tune a LoRA adapter on Stable Diffusion XL — the most common LoRA training target for style and subject customization in ComfyUI workflows.

Train a brand style LoRA

Fine-tune a LoRA on a brand's existing visual assets (marketing images, product renders) so future generations match a consistent brand look.

Train a character LoRA

Fine-tune a LoRA on a specific character (original IP, illustrated, or photoreal) so it can be reproduced consistently across poses and scenes.

Train a product LoRA

Fine-tune a LoRA on a specific product (packaging, shape, logo placement) so it can be generated in new scenes and backgrounds without a full photoshoot.

Train a person LoRA

Fine-tune a LoRA on a specific person's likeness from reference photos, for consistent portraits and scenes — subject to Badgr's usage policy for likeness training.

Train a general art style LoRA

Fine-tune a LoRA on a visual art style (illustration, painting technique, render style) independent of any single subject or character.

Resume LoRA training from a checkpoint

Continue a previous LoRA training run from its last saved checkpoint — for extending training after hitting a max-cost limit, or fine-tuning further after review.

Compatible GPU routes

A100 40GB A100 80GB A6000 48GB H100 80GB

Example command

badgr run "python train_lora.py --config lora.yaml" \
  --gpu A100_40GB \
  --max-cost 15 \
  --max-runtime 240

Common failure modes

Training job exceeds max-cost before convergence

Lower batch size or rank, or split training into checkpointed resumable runs.

Out of memory during gradient accumulation

Move to A100 80GB or enable gradient checkpointing / 8-bit optimizers.

Dataset upload times out on job start

Serve model Check live route

View details →