Controllable FLUX.2 generation and editing for typography, fine detail, and deliberate tuning.
Brands
Black Forest Labs
FLUX image and video generation, editing, and purpose-built media tools from Black Forest Labs.
Models
Image
FLUX.2
View details →FLUX.2 covers text-to-image creation and, where exposed by the selected version, editing from one or more reference images. The variants differ deliberately: [klein] favors fast iteration, [pro] targets general production work, [flex] exposes finer generation control, and [max] prioritizes final assets and can use grounding search. Detailed prompts are especially important for [klein], which does not rely on prompt upsampling.
Fast FLUX.2 [klein] 4B generation and reference-image editing.
Fast FLUX.2 [klein] 9B generation and editing with a balance of detail and throughput.
Highest-end FLUX.2 generation and editing for final assets, with grounding search when requested.
Production-oriented FLUX.2 generation and multi-reference image editing.
Compact FLUX.2 [klein] 4B text-to-image generation for rapid drafts.
Models
Video
FLUX.3 Video
View details →FLUX.3 Video infers text-to-video, timestamped image-to-video, or video continuation from the supplied media. It supports automatic or explicit duration, multiple aspect ratios, optional synchronized audio, HD draft previews, and HD or FHD final output. The separate Draft Enhance model reproduces a saved preview at full quality from its private cache.
FLUX.3 Draft Enhance reproduces an owned saved draft at final HD or Full HD quality.
Current FLUX.3 video generation endpoint with inferred text, timed-image, and continuation workflows plus draft previews.
Models
Enhance
FLUX Tools
View details →FLUX Tools is a collection of four separate image workflows rather than a single enhancement model. Choose Erase for masked cleanup, Outpainting for extending a composition, Virtual Try-On for combining person and garment images, or Deblur for recovering a soft source. Each tool asks for different input assets, so select the workflow before preparing the image.
Remove selected image content with a white-on-black mask and reconstruct the cleared area.
Extend an image beyond its original borders with canvas size, placement, and optional text guidance.
Visualize a garment on a person from separate person and product images.
Recover usable sharpness and local detail from a blurred source image.