Black Forest Labs
Baden-Württemberg, 德国FLUX 3 Action is Black Forest Labs' announced action-prediction product built on the FLUX 3 audiovisual backbone. Initial access is through selected research and commercial partners, beginning with the FLUX-mimic collaboration for robotic manipulation.
FLUX 3 Dev is Black Forest Labs' announced open-weight FLUX 3 backbone for video, audio, image content creation, and action prediction. Checkpoint details, license terms, and a release date have not yet been published.
FLUX Video Upscale is a video upscaling model from Black Forest Labs. It enlarges a single source video by 1.5× to 3× while preserving its duration, with an optional prompt...
FLUX 3 Video is Black Forest Labs' generally available audiovisual generation model. It supports text-to-video, image-to-video with up to ten keyframes, video continuation, multilingual dialogue, synchronized audio, draft previews, and clips up to 20 seconds.
FLUX 3 Image is Black Forest Labs' announced image synthesis and editing product built from the unified FLUX 3 multimodal foundation. Its public early-access release is planned after the initial Video rollout.
Flux 2 Klein 4B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.
Flux 2 Klein 9B is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.
Flux 2 Max is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet.
Flux 2 Dev is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.
FLUX.2 [flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture. It supports text and image inputs for generation, restyling, or edit-style workflows.
A high-end image generation and editing model focused on frontier-level visual quality and reliability. It supports text and image inputs for generation, restyling, or edit-style workflows.
Compact 5.6B open-weight FLUX 3 image generation and editing model with multi-reference and bounding-box support.
Prompt-based editing of an existing video, preserving source duration and aspect ratio, with output capped at 720p.
Flux 1 Dev is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.
Flux 1 Kontext Max is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet.
A high-end image generation and editing model focused on frontier-level visual quality and reliability. It supports text and image inputs for generation, restyling, or edit-style workflows.
Flux 1 Schnell is the fastest and most cost-effective model in the FLUX.2 family, optimized for high-throughput use cases while maintaining excellent image quality.
A high-end image generation and editing model focused on frontier-level visual quality and reliability. It supports text and image inputs for generation, restyling, or edit-style workflows.
A high-end image generation and editing model focused on frontier-level visual quality and reliability. It supports text and image inputs for generation, restyling, or edit-style workflows.