Flux：具有 12B 参数的开源文本到图像模型

Flux：具有 12B 参数的开源文本到图像模型
Flux: Open-source text-to-image model with 12B parameters

原始链接: https://blog.fal.ai/flux-the-largest-open-sourced-text2img-model-now-available-on-fal/

介绍 FLUX，这是由 Stable Diffusion 的开发者 Black Forest Labs 创建的最先进的开源文本到图像模型。它拥有超过 120 亿个参数，提供了无与伦比的创意可能性和性能，可与 Midjourney 相媲美。尝试 fal. 上的演示。该模型的三个版本现已在 fal 上提供： - FLUX.1 (dev) - 在非商业许可下开源，非常适合在社区内构建；在这里开始探索 fal Playground。 - FLUX.1 (Schnell) - 一种快速作用的变体，速度比基本模型快十倍，具有 Apache 2 许可证；在这里开始尝试 fal Playground。 - FLUX.1 (Pro) - 闭源、商业许可版本，可通过 API 访问；在这里访问 fal 游乐场。提示“一个大胡子男人的肖像......表情严肃，戴着红色墨镜，浅灰色巴塔哥尼亚羊毛夹克”用于展示模型的能力。它在温暖的黄金时段辉光和模糊的户外风景的背景下产生了一个引人注目的图像，具有粗犷而时尚的外观。此外，通过 fal 集成其先进的推理引擎，Flux 模型的运行速度是 eager torch 的两倍，确保更快的响应时间而不牺牲质量。主要功能包括增强的图像分辨率、改进的逼真人体解剖学、更好地遵守提示以及 FLUX.1 (Schnell) 模型所展示的令人印象深刻的速度。例如，当被要求描绘“戴着太阳镜的巨型土豆……躺在沙滩巾上”时，模型生成了一个异想天开的场景，其中包括色彩缤纷的沙滩玩具、打排球的拟人化水果、灯塔沙堡以及欢快的冰淇淋摊贩。轻松的海滩氛围。这凸显了模型捕捉体现乐趣、俏皮和创造力的生动图像的能力。在 fal Playgrounds 中探索更多信息或查阅 API 文档，亲自体验这些非凡的模型。

该用户讨论了一些人在人工智能讨论中将人工智能 (AI) 与纳粹德国进行比较的担忧，认为这种做法重复且不严肃。他们认为人工智能只是一种工具，就像微软画图或油画一样，任何人都可以滥用这些工具。用户分享了他们使用 Ideogram 的体验，Ideogram 是一个根据用户提示生成艺术图像的在线平台，并表示它可以生成高质量的图像并严格遵循用户指令。然而，他们表示希望有一个类似的程序可以在本地运行而不需要过滤器。他们提到尝试使用表意文字，赞扬图像质量和迅速遵守，同时指出在清晰地表达复杂的想法方面存在一些困难。他们分享了 Ideogram 的一张图像中代表的四种创意类别的示例，包括苦苦挣扎的作家、复印和粘贴艺术家、项目检索者和混音者。此外，用户还讨论了稳定扩散模型 (SD) 的演变，比较了 SD1 和 SD3，描述了 SD3 中一致性和场景组成的改进，并预测了工程图中的详细程度的进一步进展。最后，他们认为通用模型将随着时间的推移而改进，而不需要专门的专业知识。

Flux, the largest SOTA open source text-to-image model to date, developed by Black Forest Labs—the original team behind Stable Diffusion is now available on fal. Flux pushes the boundaries of creativity and performance with an impressive 12B parameters, delivering aesthetics reminiscent of Midjourney.

To play around with the model now, check out the demo page here on fal.

Prompt: Portrait of a bearded man with dark hair wearing red sunglasses and a light gray Patagonia fleece jacket. He has a serious expression and is looking directly at the camera. The background shows a blurred outdoor scene with rocky terrain and a vibrant pink and purple sunset sky. The lighting gives the image a warm, golden-hour glow. The overall mood is rugged yet stylish, with a touch of adventure.

BFL has released three three variations of the model, all available all on fal:

FLUX.1 [dev]: The base model, open-sourced with a non-commercial license for community to build on top of. fal Playground here.
FLUX.1 [schnell]: A distilled version of the base model that operates up to 10 times faster. Apache 2 Licensed. To get started, fal Playground here.
FLUX.1 [pro]: A closed-source version only available through API. fal Playground here.

Prompt: Close-up of LEGO chef minifigure cooking for homeless. Focus on LEGO hands using utensils, showing culinary skill. Warm kitchen lighting, late morning atmosphere. Canon EOS R5, 50mm f/1.4 lens. Capture intricate cooking techniques. Background hints at charitable setting. Inspired by Paul Bocuse and Massimo Bottura's styles. Freeze-frame moment of food preparation. Convey compassion and altruism through scene details.

With the integration of fal's cutting-edge inference engine, you can run Flux models up to 2x faster than with eager torch. This results in faster processing times while maintaining the exceptional quality and detail.

Key Features:

Enhanced Image Quality: Generate stunning visuals at higher resolutions.
Advanced Human Anatomy and Photorealism: Achieve highly realistic and anatomically accurate images.
Improved Prompt Adherence: Get more accurate and relevant images based on your inputs.
Exceptional Speed: Benefit from the speed and efficiency of Flux Schnell, ideal for high-demand applications.

Prompt: A giant potato in sunglasses and a Hawaiian shirt lounges on a beach towel surrounded by colorful beach balls and flip-flops. Nearby, anthropomorphic fruits play beach volleyball. In the background, a lighthouse sand sculpture stands next to an ice cream truck with a giant cone, serving treats to cheerful beachgoers. The scene captures a fun, playful summer vibe with the sound of waves crashing nearby.

Visit the fal Playgrounds or the API documentation and see firsthand how epic these models are.

Flux：具有 12B 参数的开源文本到图像模型 Flux: Open-source text-to-image model with 12B parameters

Key Features:

Flux：具有 12B 参数的开源文本到图像模型
Flux: Open-source text-to-image model with 12B parameters