Researchers just released Mr. Flow, a training-free framework that accelerates text-to-image models by 9x to 21x. It drafts quickly at low resolution, upscales with subtle noise, and refines high-frequency details in the final step, slashing wait times to around one second without hurting quality.
Nvidia just launched a workflow bridging Blender with the FLUX.1 image generator, allowing creators to guide AI images using 3D scenes. Instead of endlessly tweaking text prompts, you can place rough 3D models and set camera angles to lock down the layout. The catch is that it requires an RTX 4080 GPU or higher to run.
xAI just dropped Grok-2 and Grok-2 mini into beta, claiming the flagship model beats Claude 3.5 Sonnet and GPT-4 Turbo on the LMSYS leaderboard. Alongside major jumps in reasoning and coding, xAI partnered with Black Forest Labs to bring FLUX.1 image generation straight to 𝕏. It is currently rolling out to 𝕏 Premium subscribers, with an enterprise API arriving later this month.
Black Forest Labs just launched with a $31M seed round led by Andreessen Horowitz and released FLUX.1, a new 12B-parameter text-to-image suite. Created by researchers behind Stable Diffusion, the suite features pro, dev, and schnell versions, delivering top-tier prompt adherence and visual detail that surpasses Midjourney v6.0. Next on the roadmap: text-to-video models.
