Meet the team that turns your ideas into work.

Discover EightBots
EIGHTBOTS
Contact salesSign up
AI provider

Black Forest Labs

Black Forest Labs is an independent visual AI company founded in 2024. Its headquarters are in Freiburg im Breisgau, Germany, and it also operates a lab in San Francisco. Co-founder Robin Rombach is CEO.

Explore models

Models & tools

  • Distilled 5.6-billion-parameter image transformer for generation, editing and compositions with up to ten references.

    Launch date not confirmedAPI · Downloadable · Provider product

  • Four-billion-parameter image generation and reference-editing model distilled to four sampling steps.

    Launch date not confirmedAPI · Downloadable · Provider product

  • Hosted image generation and editing model with a fixed-snapshot standard endpoint.

    Launch date not confirmedAPI · Provider product

  • Image generation and editing model with up to ten reference images and bounding-box layout controls.

    Launch date not confirmedAPI · Provider product

  • High-capacity hosted image model for generation and reference-image editing.

    Launch date not confirmedAPI · Provider product

  • Hosted image model for text rendering and small visual details, with sampling-step and guidance controls.

    Launch date not confirmedAPI · Provider product

  • Video generation model with synchronized audio, timed image keyframes and existing-video input.

    Launch date not confirmedPreviewAPI · Provider product

  • Video super-resolution model with precise and creative modes that retains the original audio.

    Launch date not confirmedAPI

  • Seven-billion-parameter world-action model that jointly predicts future visual frames and robot action sequences.

    Launch date not confirmedDownloadable

  • Seven-billion-parameter robot policy that generates joint commands and future frames from DROID-style observations.

    Launch date not confirmedDownloadable

  • Seven-billion-parameter SO-101 robot policy that predicts actions and future frames from cameras, robot state and task instructions.

    Launch date not confirmedDownloadable

  • Undistilled 5.6-billion-parameter image model for generation, editing, fine-tuning and LoRA training.

    Launch date not confirmedDownloadable

  • Nine-billion-parameter Qwen3.5-based vision-language model that expands image requests into detailed captions.

    Launch date not confirmedDownloadable

  • FLUX 3 video model post-trained by fal Research with Black Forest Labs for text, image and keyframe inputs.

    Launch date not confirmedAPI · Provider product

  • Prompt-free image restoration model that improves sharpness while aiming to retain the original scene and composition.

    Launch date not confirmedAPI

  • Image editing model that removes objects or regions selected by a black-and-white mask.

    Launch date not confirmedAPI

  • Image outpainting model with controls for canvas dimensions and source-image placement.

    Launch date not confirmedAPI

  • Text-guided video editing model for object replacement, style changes, scene changes and dialogue edits.

    Launch date not confirmedAPI

  • Virtual clothing try-on model that combines person and garment images at resolutions up to four megapixels.

    Launch date not confirmedAPI

  • Twelve-billion-parameter text-to-image transformer trained with guidance distillation.

    Launch date not confirmedAPI · Downloadable

  • Twelve-billion-parameter text-to-image model that generates images in one to four sampling steps.

    Launch date not confirmedDownloadable

  • Twelve-billion-parameter image model that combines text prompts with Canny-edge structure.

    Launch date not confirmedDownloadable

  • Twelve-billion-parameter image model guided by text instructions and a depth map.

    Launch date not confirmedDownloadable

  • Image expansion model with independent controls for generation beyond each side of an existing image.

    Launch date not confirmedAPI · Provider product

  • Twelve-billion-parameter inpainting model that fills selected image regions using text and surrounding context.

    Launch date not confirmedDownloadable

  • Hosted inpainting model that fills a masked image area from a text prompt.

    Launch date not confirmedAPI · Provider product

  • Twelve-billion-parameter image-editing transformer with text instructions and character, object or style references.

    Launch date not confirmedDownloadable

  • Premium hosted variant of Kontext for image generation and editing.

    Launch date not confirmedAPI · Provider product

  • Hosted Kontext model for text-guided image creation and editing.

    Launch date not confirmedAPI · Provider product

  • Twelve-billion-parameter image generator developed with Krea for photographic aesthetics.

    Launch date not confirmedDownloadable

  • Image-conditioning adapter for FLUX.1 generators that supports variations and restyling.

    Launch date not confirmedDownloadable

  • A 32-billion-parameter rectified-flow transformer for image generation and editing with multiple references.

    Launch date not confirmedDownloadable

  • Nine-billion-parameter rectified-flow image model with four-step generation and reference editing.

    Launch date not confirmedAPI · Downloadable · Provider product

  • Undistilled four-billion-parameter image model for generation, reference editing and fine-tuning.

    Launch date not confirmedDownloadable

  • Undistilled nine-billion-parameter image generation and editing checkpoint for adaptation and custom pipelines.

    Launch date not confirmedDownloadable

  • Hosted image generator with text prompts and optional image prompts through Redux conditioning.

    Launch date not confirmedAPI · Provider product