Black Forest Labs (BFL), a startup founded by the creators of the popular Stable Diffusion AI image generation model that underpins many AI image generation apps and services (such as MidJourney), has announced the release of a new, faster text-to-image model called Flux 1.1 Pro, and with it, a paid application programming interface (API) on which developers can build third-party apps powered by the model (or incorporate it into their existing apps). We are excited to release FLUX1.1 [pro], our most advanced and efficient model yet, alongside the general availability of the beta BFL API. pic.twitter.com/EKRb0APJJF — Black Forest Labs (@bfl_ml) October 3, 2024 Individual users can access the new Flux 1.1 Pro model not directly through Black Forest Labs’ website but through its partners such as together.ai, Replicate, fal.ai, and Freepik. What a time to be alive! — Philippe Tremblay (@philtrem22) October 4, 2024 This performance boost places it ahead of competitors like MidJourney and Ideogram. The release of Flux 1.1 Pro, however, comes with unresolved questions about its training dataset. 3x cheaper it should be if 3x faster as it uses less gpu time? But no … — Dimitar (@dvebene) October 3, 2024 Generative AI companies have faced scrutiny, particularly Stability AI and MidJourney, as they continue to be embroiled in lawsuits by artists accusing the firms of copyright infringement for using human-created images found online without proper consent or compensation. As of now, one key class action lawsuit remains in court. This takes generative images even one step further, it’s getting really hard to grasp this insane rate of improvement — Azhar Ahmed (@IAmAzharAhmed) October 3, 2024 Unlike the free and open-source Flux.1 model, Flux 1.1 Pro is a proprietary offering designed for commercial and enterprise use only, signaling a shift in BFL’s business strategy. The company views the launch of this new API and model as pivotal in its evolution, offering developers and enterprises customizable, high-quality image-generation tools. So this is the Bluberry model that everybody was talking about in the LLM arena — Alejandro Capellán | IA y Negocios Digitales (@alekzan) October 3, 2024 Tested under the codename “blueberry,” the model achieved the highest Elo score of 1153, surpassing other generative models like MidJourney 6.1 (Elo score 1100) and Ideogram v2 (score 1108). Its fast image generation capabilities allow workflows to prioritize speed without compromising quality, producing outputs up to three times faster than its predecessor, Flux 1.0 Pro. if its really 6 times faster and better quality, its pretty amazing — saqib (@saq1b_) October 3, 2024 Soon, Flux 1.1 Pro will support ultra-high-resolution images up to 2k, a highly anticipated feature that will maintain precision and speed even with larger outputs. The model’s high performance and versatility make it an appealing choice for industries such as design, advertising, and entertainment, where the demand for high-quality AI-generated media is constantly growing. Should we expect only the Pro version to be updated? — Tibo (@tibo_maker) October 3, 2024 The API offers advanced customization, including the ability to adjust model choice, resolution, and content moderation, making it scalable for both small projects and enterprise-level applications. The pricing model is competitive, starting at $0.04 per image for Flux 1.1 Pro and $0.05 per image for the older Flux 1.0 Pro model, making it an attractive option for users seeking high-quality outputs without excessive costs. Looks awesome I wonder when it’ll make its way to Grok 👀 — XHabib (@RealXHabib) October 3, 2024 The earlier Flux 1.0 model had been widely regarded as a milestone in the AI community. Co-founders Robin Rombach, Patrick Esser, and Andreas Blattmann brought their expertise from Stability AI, the team behind Stable Diffusion, into this new venture, aiming to make generative AI tools more accessible. Generative images have become so advanced that even my humble requests for custom cat portraits are being returned as Salvador Dalí paintings. — Ashok (@ashok_hey) October 3, 2024 However, with the introduction of the proprietary Flux 1.1 Pro, BFL is pivoting toward a more commercial strategy while still offering powerful and customizable tools for developers and enterprises. Black Forest Labs’ move to release Flux 1.1 Pro comes at a time of heightened competition in the generative AI space. Just like a real photos, amasing. — Haezl (@Haezl_Crypto) October 4, 2024 This has pushed BFL to continue innovating. Unlike many of its rivals, BFL’s focus on offering ultra-high-resolution image generation and faster performance is seen as key differentiators. Started to use mystic few days ago, and now something new again 😂 — Aleksandr Smetanka (@asmetanka) October 3, 2024 Flux Pro 1.1 is a game-changer. I’ve been experimenting with it on Freepik and the results are mind-blowing. The progress in generative images is stunning, making it harder to distinguish reality from AI-generated content. — David Chen (@TechArtDoc) October 3, 2024 October 4, 2024: New ChatGPT Canvas Interface by OpenAI for Coders and Writers September 26, 2024: Meta AI Enhances User Experience with New Image Generation and Photo Editing Tools August 23, 2024: Free to Create: Google’s Bard Rolls Out Zero-Cost Text-To-Image Generator August 15, 2024: Musk’s xAI Unveils Grok-2 Which can also Generate Politician and Brand Images August 13, 2024: Dark Web Sees Alarming Surge in Demand for AI-Generated Abuse Images! For more news and insights, visit AI News on our website.
This means that companies offering creative tools can add Flux as an option to their offerings, provided they (and their end users) are willing to pay the API costs.
Some of these services refer to the model under different names, such as “Flux Fast.” The Flux 1.1 Pro model promises improved prompt adherence and diversity, delivering six times faster image generation speeds compared to its predecessor.
This release follows the earlier success of the original open-source Fluxmodel, which powers Elon Musk’s Grok 2 chatbot from xAI.
Codenamed “Blueberry,” Flux 1.1 Pro now holds the top spot on the Artificial Analysis image arena leaderboard, a third-party benchmark platform for comparing AI model performance.
In addition to this, BFL has updated its original Flux 1.0 Pro model, doubling its generation speed to enhance overall efficiency.
With the launch of the BFL API, developers now have the opportunity to integrate state-of-the-art image generation capabilities into their applications.
Building on its initial success, Black Forest Labs continues to draw attention. Just two months ago, the company raised $31 million in seed funding led by Andreessen Horowitz, with notable backers like Brendan Iribe, Michael Ovitz, and Garry Tan.
The open-source nature of Flux 1.0 Dev and Flux 1.0 Schnell had positioned BFL at the center of the debate over open-source versus proprietary AI, especially as its 12-billion parameter architecture allowed it to compete with models like MidJourney and DALL-E.
Companies like MidJourney, Stability AI, Pika, Runway, and Luma are all developing competitive text-to-image and image-to-video models.
Thanks, I’ll definitely try!
Looking to the future, BFL has already set its sights on expanding its generative AI capabilities beyond images. The company is working on text-to-video systems, a development that could further solidify its leadership in AI-driven media.
If successful, this could disrupt industries like advertising, content creation, and virtual reality, further raising the stakes for competitors like MidJourney, which is also pursuing generative AI video models.
Black Forest Labs Rolls Out Flux 1.1 Pro Along with New API for Developers!
-
Midhat Tilawat is endlessly curious about how AI is changing the way we live, work, and think. She loves breaking down big, futuristic ideas into stories that actually make sense—and maybe even spark a little wonder. Outside of the AI world, she’s usually vibing to indie playlists, bingeing sci-fi shows, or scribbling half-finished poems in the margins of her notebook.Midhat Tilawat
Midhat Tilawat is endlessly curious about how AI is changing the way we live, work, and think. She loves breaking down big, futuristic ideas into stories that actually make sense—and maybe even spark a little wonder. Outside of the AI world, she’s usually vibing to indie playlists, bingeing sci-fi shows, or scribbling half-finished poems in the margins of her notebook.
Key Takeaways:
Was this article helpful?
YesNo
Midhat Tilawat is endlessly curious about how AI is changing the way we live, work, and think. She loves breaking down big, futuristic ideas into stories that actually make sense—and maybe even spark a little wonder. Outside of the AI world, she’s usually vibing to indie playlists, bingeing sci-fi shows, or scribbling half-finished poems in the margins of her notebook.
