FLUX
Image generation model family from Black Forest Labs
FLUX is Black Forest Labs' family of generative image models for text-to-image generation and image editing, available through BFL APIs and open-weight releases, with variants including FLUX.1, FLUX.1 Kontext, FLUX.2, FLUX.2 Klein/Max, FLUX 1.1 Pro, and FLUX Tools.
Pricing
Pricing is published per image and appears to vary by FLUX variant on the vendor's official pricing materials; this record captures the flagship public per-image rate associated with FLUX.1 [pro].
Black Forest Labs publishes first-party public pricing for the FLUX image-generation offering on its official docs/pricing pages. The publicly listed image price recorded here is the flagship FLUX.1 [pro] rate.
Model Intelligence
Recent stories
Black Forest Labs said Martin Scorsese joined as a partner and advisor and appeared in a working FLUX storyboard session. The endorsement gives generative pre-production a major filmmaker name; watch for more creator reaction and film workflow adoption.
Black Forest Labs released FLUX Virtual Try-On with demo and API access, claiming sub-4-second generations across thousands of products while preserving identity and garment details. The pitch targets catalog-scale apparel imagery, so teams should try it where logos, prints, and fit consistency usually break first.
Stages AI posts say creators can now sign up for limited early accounts ahead of its May 1 public opening. The preview also details 11 in-app LoRA training modes, automated quality scoring, and a Photoshop-like editor planned for next month, so watch for pricing and access limits.
Threads outlined multi-step pipelines for turning sketches into photoreal scenes, placing furniture with red-box prompts, and swapping in a real face after generation. Prompt-only inpainting still misses precise placement, so creators are using masks, ControlNet, and cleanup passes for tighter control.
Black Forest Labs says FLUX.2 [klein] 9B is now up to 2x faster for multi-reference editing at the same price, with new FP8 weights for leaner local runs. Retest reference-heavy edit pipelines if speed or local deployment was a blocker.