
FLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.
![LoRA trainer for FLUX.1 Kontext [dev]](https://refinery.fal.media/url/https%3A%2F%2Fv3.fal.media%2Ffiles%2Fmonkey%2FpYXiffttc2Skv36wflufu_dec4efe0d27e4527b64acfbc0e91536a.jpg/tr:w-1920,q-80/pYXiffttc2Skv36wflufu_dec4efe0d27e4527b64acfbc0e91536a.webp)
LoRA trainer for FLUX.1 Kontext [dev]

Train styles, people and other subjects at blazing speeds.

Train custom LoRAs for Wan-2.1 T2V 14B

Qwen Image LoRA training
![Fine-tune FLUX.2 [klein] 4B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.](https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a8b082e%2FN8Fy12FSedqMd-2Ehh8z1_70e50238ee6b479ebd61270840b4806e.jpg/tr:w-1920,q-80/N8Fy12FSedqMd-2Ehh8z1_70e50238ee6b479ebd61270840b4806e.webp)
Fine-tune FLUX.2 [klein] 4B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.
![Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.](https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a8b082b%2F4dsf0LE8NoXuk9Pz0Ziue_d7c1c380c4d04e03b820d06500a5749f.jpg/tr:w-1920,q-80/4dsf0LE8NoXuk9Pz0Ziue_d7c1c380c4d04e03b820d06500a5749f.webp)
Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.
![Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.](https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2Ftiger%2FnYv87OHdt503yjlNUk1P3_2551388f5f4e4537b67e8ed436333bca.jpg/tr:w-1920,q-80/nYv87OHdt503yjlNUk1P3_2551388f5f4e4537b67e8ed436333bca.webp)
Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains.

Train LoRAs on Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

LoRA trainer for Qwen Image Edit 2511