Official

black-forest-labs / flux-1.1-pro-ultra-finetuned

Inference model for FLUX 1.1 Pro Ultra using custom `finetune_id`. Supports 4MP images and raw mode for realism

  • Public
  • 1.3K runs
  • Paper
  • License
Run with an API
Playground API Examples README

FLUX 1.1 Pro Ultra - Finetuned

About

This model builds upon FLUX 1.1 Pro - Ultra Mode, adding the powerful capability to use custom finetunes. It leverages the high-resolution capabilities of FLUX 1.1 [pro], supporting up to 4MP images while maintaining an impressive generation time of approximately 10 seconds per sample, and allows you to apply your specific trained styles or concepts.

Finetuning

This model requires a finetune_id corresponding to a finetune you have trained.

  • finetune_id (required): Provide the ID of your trained finetune.
  • finetune_strength (optional, default=1): Control the influence of your finetune on the final output. Values range from 0 (no finetune effect) to 2 (stronger effect).

To train your own finetune, please visit the training page: black-forest-labs/flux-1.1-pro-ultra-finetuned

Higher Resolution, No Compromise in Speed

FLUX 1.1 [pro] – ultra mode capabilities are retained: This model enables image generation at four times the resolution of standard FLUX 1.1 [pro], without sacrificing prompt adherence. Unlike many high-resolution models that experience significant slowdowns at higher resolutions, our performance benchmarks show sustained fast generation times—over 2.5x faster than comparable high-resolution offerings.

Raw Mode

FLUX 1.1 [pro] – raw mode: For creators seeking authenticity, the raw mode captures the genuine feel of candid photography. Toggle this feature (raw: true) to generate images with a less synthetic, more natural aesthetic. Compared to other text-to-image models, raw mode significantly increases diversity in human subjects and enhances the realism of nature photography.

License

By using FLUX 1.1 [pro] - ultra finetuned through Replicate you agree to the Black Forest Labs API agreement and the Black Forest Labs Terms of Service.