- 🆕 Black Forest Labs' next-gen image model, released November 2025.
- 🎯 Photorealistic generation with strong prompt fidelity and complex scene composition.
- 🧠 Couples Mistral-3 24B vision-language model with rectified flow transformer.
- 👁️ Multi-reference input for character, product, and style consistency.
- 💬 Improved complex text rendering, typography, and UI mockups.
- 🔧 Unifies generation and editing within a single architecture.
- 🏢 Production-ready API endpoint within the open-core Flux 2 family.
Black Forest Labs is a generative AI company based in Freiburg im Breisgau, Germany, founded by former members of Stability AI. The lab is best known for developing the Flux family of text-to-image models, which generate images from natural language prompts and have quickly…
Explore 2 more models by Flux (text-to-image model) →Flux 2 Pro is the production-tier text-to-image and editing model in Black Forest Labs' Flux 2 family, released on November 25, 2025. It sits alongside its larger sibling Flux 2 Max and the editing-focused Flux 2 Max (Edit), with the broader lineup spanning managed APIs and open-weight checkpoints. Black Forest Labs positions Flux 2 Pro as a fast, precise workhorse for photorealistic output, complex scene composition, and reliable prompt adherence.
Architecturally, Flux 2 builds on a latent flow matching approach that combines generation and editing in a single design. The model couples the Mistral-3 24B parameter vision-language model with a rectified flow transformer—the VLM contributes real-world knowledge and contextual understanding, while the transformer handles spatial relationships, material properties, and compositional logic. It supports multi-reference input for maintaining character, product, and style consistency across outputs.
Compared with the earlier Flux 1 generation, Black Forest Labs describes Flux 2 as capturing compositional logic that earlier architectures could not render, with improved text rendering for typography, infographics, and UI layouts that previously suffered from garbled letters.
Black Forest Labs reports running third-party safety evaluations on the Flux 2 checkpoints, including filtering and fine-tuning to mitigate generation of unlawful content before release. As the company frames it, Flux 2 Pro targets prompt adherence and visual fidelity while generating images faster and at lower cost than its own prior tiers.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | $ / img | Categories | API |
|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 100.00 | #2 | $0.015 | image,creative | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #1 | $0.01 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.035 | image,creative,router,fallback | openai-images |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = on-chain trust (0-100). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.