A style LoRA for black-forest-labs/FLUX.1-schnell, trained on the watercolor configuration of thangvip/compliment-forest-multistyle-v2. The v2 dataset balances animals, people, symbolic objects, and environments rather than teaching an animal-only subject prior.

Include cmprst_watercolor near the beginning of the prompt.

Run details are included in training-summary.json. The adapter repository is thangvip/compliment-forest-watercolor-flux-lora-v2.

Training images were generated specifically for this project with black-forest-labs/FLUX.1-schnell through Hugging Face Inference Providers. No named artist or known character was requested. Use remains subject to the base model's license and terms.