AgentHubAgentHub

AI tools·Image & video·Global

FLUX.1

Frontier image foundation models by former Stable Diffusion creators, excelling at prompt adherence & text.

9.8/ 10.0Editorial Rating
Editorial score based on public benchmarks and community feedback — not a third-party benchmark result

Compiled through 2026-09

FLUX.1 visual
Limited in ChinaFree / openOpen sourceSelf-hostableImageLow costCompare

Open weights, fully local via ComfyUI

Vendor
Black Forest Labs
Started
2024
China availability
Limited in ChinaReachable but constrained: may need your own API key, an invite, or unstable routing
Pricing tier
Free / open
Current flagship
FLUX.1 [dev] / [pro] / [schnell]
Website
blackforestlabs.ai

Evaluation, Pros & Cons

Editorial score based on public benchmarks and community feedback — not a third-party benchmark result

Key Advantages

  • Open-weights image generator king; photorealism, anatomy, and typography are unmatched
  • Natively supported in ComfyUI for local private hosting with thriving LoRA ecosystem

Limitations & Caveats

  • Local dev model requires substantial GPU VRAM (16GB+ recommended)

Overview

FLUX.1 is a suite of 12B parameter rectified flow models by Black Forest Labs. It is renowned for surpassing Midjourney in complex typography rendering and prompt adherence, while offering open weights for local ComfyUI deployment.

Direction

Developing next-generation video foundation models and real-time on-device variants.

Version history

  1. Nov 2024

    Latest

    FLUX.1 Tools

    Official Inpainting and Depth suites.

  2. Aug 2024

    FLUX.1 released

    Released schnell, dev, and pro tiers.