紧跟着 Sora，搞 AI 的大厂都纷纷坐不住了。
昨天刚写完谷歌的 Gemma，开源 2B 和 7B 大模型、效果比肩 LLAMA2，最强开源大模型易主。
今天，又有新炸弹。
就在深夜，Stability AI 放出了 Stable Diffusion 3.0，宣称在图片质量、文字渲染等方面大大提升，并且采用和 Sora 同样的 DIT 架构。
不止如此，Midjourney 也放出了消息。
Midjourney Video 随 v7 一起推出！
据称，他们早在 Sora 之前就已经在研究了。
静待 2024AI 视频的爆发吧。
Stable Diffusion 3.0 的效果
欣赏下 #SD3 的效果。
这些都来自 StabilityAI 的官方网站，还有他们的负责人社交网站。
总共 20 个。
史诗般的动画艺术作品，描绘了一位巫师在夜间在山顶上向黑暗的天空施放宇宙咒语，上面写着由彩色能量制成的“Stable Diffusion 3”
Prompt: Epic anime artwork of a wizard atop a mountain at night casting a cosmic spell into the dark sky that says "Stable Diffusion 3" made out of colorful energy
教室桌子上有一个红苹果的电影照片，黑板上用粉笔写着“go big or go home”
Prompt: cinematic photo of a red apple on a table in a classroom, on the blackboard are the words "go big or go home" written in chalk
一幅宇航员骑着一头穿着芭蕾舞短裙、撑着粉色雨伞的猪的画，猪旁边的地上是一只戴着礼帽的知更鸟，角落里写着“stable diffusion”字样
Prompt: a painting of an astronaut riding a pig wearing a tutu holding a pink umbrella, on the ground next to the pig is a robin bird wearing a top hat, in the corner are the words "stable diffusion"
角落里写着“stable diffusion”字样 , 看生成的还真是在左下角，NB
黑色背景下变色龙的工作室照片特写
Prompt: studio photograph closeup of a chameleon over a black background
厨房的桌子上放着一块绣有“good night”字样的绣花布和一只绣有小老虎的绣花布。布旁边有一支点燃的蜡烛。灯光昏暗而引人注目
Prompt: Resting on the kitchen table is an embroidered cloth with the text 'good night' and an embroidered baby tiger. Next to the cloth there is a lit candle. The lighting is dim and dramatic.
肥猫看向一边，坐在绿色的草坪上。自然界中一只毛茸茸的白猫，蓝眼睛的肖像，特写。
Prompt: The fat cat looks to the side and sits on a green lawn. Portrait of a fluffy white cat with blue eyes in nature, close-up.
木桌上有三个透明玻璃瓶。左边的有红色液体，数字 1。中间的有蓝色液体，数字 2。右边的有绿色液体，数字 3。
Prompt: Three transparent glass bottles on a wooden table. The one on the left has red liquid and the number 1. The one in the middle has blue liquid and the number 2. The one on the right has green liquid and the number 3.
有网友还做了和 midjourney、dall e 的对比。
Same prompt on Midjourney
Same prompt with dall e
一张 90 年代台式电脑放在办公桌上的照片，电脑屏幕上写着“欢迎”。在背景墙上我们看到墙上有非常漂亮的涂鸦，上面写着“SD3”。
Prompt: Photo of an 90's desktop computer on a work desk, on the computer screen it says "welcome". On the wall in the background we see beautiful graffiti with the text "SD3" very large on the wall.
提示：一辆跑车的夜间照片，侧面写着“SD3”文字，汽车在赛道上高速行驶，巨大的路标上写着“faster”的文字
Prompt: Night photo of a sports car with the text "SD3" on the side, the car is on a race track at high speed, a huge road sign with the text "faster".
一匹马在绿草如茵、背景是一座山的田野里的一个彩色球上保持平衡。
Prompt: A horse balancing on top of a colorful ball in a field with green grass and a mountain in the background.
动画风格的插图，在一个小草山的顶部有一个报摊，在报摊的顶部我们看到文字“it's here!”。在背景中，我们看到一场大雨即将来临。
Prompt: Anime style illustration of a newsstand on top of a small grassy hill, on top of the newsstand we see the text "it's here!". In the background we see a big rain approaching.
在银河下拍摄的树木，月亮和暮光照射在山谷上。满月高高地挂在天空中，暮色的光芒仍然可见。
Prompt: Trees photographed under the Milky Way, the moon and twilight shine on the Valley. The full moon appears high in the sky and the twilight glow can still be seen.
这是一幅原创酒精水墨画，通过抽象多彩的背景展示现代艺术，类似大理石纹理。它非常适合现代横幅，并为图形设计提供了飘逸的触感。
Prompt: This is an original alcohol ink painting that showcases modern art through an abstract and colorful background, resembling marble texture. It's perfect for modern banners and offers an ethereal touch to graphic design.
鱼眼镜头拍摄的海浪撞击苏格兰灯塔的照片，黑色的海浪。
Prompt: Fisheye lens photo where waves hit a lighthouse in Scotland, black waves
职业拳击手挥拳剪影的照片，专业运动展现力量。环境很暗，只有背光照亮战斗机。环境中烟雾弥漫，营造出黑暗的体育馆气氛。
Prompt: Professional photo of a silhouette of a fighter throwing a punch, professional sport showing strength. The environment is dark with only a backlight that illuminates the fighter. There is smoke in the environment creating a dark sports hall atmosphere.
海滩上一艘沉船的宽幅照片，船上有大量的铁锈和苔藓，与美丽的蓝色海水和自然之美所传达的和平形成鲜明对比。大浪磅礴，触碰着船。
Prompt: Wide photo of a shipwreck on the beach, lots of rust and moss on the ship contrasting with the beautiful blue of the ocean water and the peace that the beauty of nature conveys. The big waves are magnificent and touch the ship.
玻璃桌上放着一本杂志，杂志封面上写着“难以置信”的文字。桌子位于舒适房间的中央，房间里有两张非常舒适的紫色沙发。
Prompt: A magazine on a glass table, the magazine has the text "incredible" on the cover. The table is in the center of a comfortable room with two very cozy purple sofas.
各种南瓜的喜怒无常的静物画。
Prompt: Moody still life of assorted pumpkins.
PS: 嗯哼？😂😂😂 喜怒无常呢？我翻译错了？还是生成的 bug 图
长方形橙色霓虹灯标志的照片，上面写着“even more stable”，标志位于地铁站的墙上，背景是地铁飞驰而过，透视照片。
Prompt: Photo of a rectangular orange neon sign with the text "even more stable", the sign is on the wall in a metro station, subway speeding by in the background, perspective photo.
看完上面的这些例子，文字渲染做的确实不错，能理解的更好了。
想去申请候补的赶紧去吧：https://stability.ai/stablediffusion3
别去晚了，和春节火车票一样，候补到最后都候补不到，mmp
下面是官方的 News。
官方 News
Announcing Stable Diffusion 3 in early preview, our most capable text-to-image model with greatly improved performance in multi-subject prompts, image quality, and spelling abilities.
宣布推出 Stable Diffusion 3 的早期预览版，这是我们功能最强大的文本到图像模型，在多主题提示、图像质量和拼写能力方面大大提高了性能。
While the model is not yet broadly available, today, we are opening the waitlist for an early preview. This preview phase, as with previous models, is crucial for gathering insights to improve its performance and safety ahead of an open release. You can sign up to join the waitlist here.
虽然该模型尚未广泛使用，但今天，我们正在开放候补名单以进行早期预览。与以前的模型一样，此预览阶段对于在开放版本之前收集见解以提高其性能和安全性至关重要。您可以在此处注册加入候补名单。
候补地址 ：https://stability.ai/stablediffusion3
The Stable Diffusion 3 suite of models currently range from 800M to 8B parameters. This approach aims to align with our core values and democratize access, providing users with a variety of options for scalability and quality to best meet their creative needs. Stable Diffusion 3 combines a diffusion transformer architecture and flow matching. We will publish a detailed technical report soon.
Stable Diffusion 3 型号套件目前范围从 800M 到 8B 不等。这种方法旨在与我们的核心价值观保持一致，并使访问民主化，为用户提供各种可扩展性和质量选项，以最好地满足他们的创意需求。Stable Diffusion 3 结合了扩散变压器架构和流量匹配 。我们将很快发布详细的技术报告。
备注：和 Sora 一样，使用 DIT 架构。
We believe in safe, responsible AI practices. This means we have taken and continue to take reasonable steps to prevent the misuse of Stable Diffusion 3 by bad actors. Safety starts when we begin training our model and continues throughout the testing, evaluation, and deployment. In preparation for this early preview, we’ve introduced numerous safeguards. By continually collaborating with researchers, experts, and our community, we expect to innovate further with integrity as we approach the model’s public release.
我们相信安全、负责任的人工智能实践。这意味着我们已经并将继续采取合理措施来防止不良行为者滥用 Stable Diffusion 3。当我们开始训练模型时，安全就开始了，并在整个测试、评估和部署过程中持续进行。为了准备这个早期预览版，我们引入了许多保护措施。通过与研究人员、专家和我们的社区不断合作，我们希望在接近模型的公开发布时进一步诚信创新。
Our commitment to ensuring generative AI is open, safe, and universally accessible remains steadfast. With Stable Diffusion 3, we strive to offer adaptable solutions that enable individuals, developers, and enterprises to unleash their creativity, aligning with our mission to activate humanity’s potential.
我们坚定不移地致力于确保生成式人工智能的开放、安全和普遍可访问。通过 Stable Diffusion 3，我们努力提供适应性强的解决方案，使个人、开发人员和企业能够释放他们的创造力，这与我们激活人类潜力的使命相一致。
If you’d like to explore using one of our other image models for commercial use prior to the Stable Diffusion 3 release, please visit our Stability AI Membership page to self host or our Developer Platform to access our API.
如果您想在 Stable Diffusion 3 发布之前探索将我们的其他图像模型之一用于商业用途，请访问我们的 Stability AI 会员页面进行自托管，或访问我们的开发人员平台以访问我们的 API。
以上，done。
我是大林，NLP 高级算法工程师，主要从事自然语言处理(NLP)、知识图谱、大模型领域的实际业务落地。 持续关注 AIGC 趋势发展，和大家一起交流 。加我微信(dalinvip2023)，备注【公众号 AIGC】，进 AIGC 交流群一起交流(还有 Sora、数字人、绘画、技术、AI 变现多方向。)
如果文章对你有一点点 🤏🏻 帮助，关注公众号并星标，可以及时收到最新 AI 信息，点赞、在看、帮忙转发给更多的朋友，是最大的支持，谢谢。