Stable Diffusion 3 Medium震撼发布 最强开源AI文生图模型！实测屌打 Midjourney，终于能在Comfyui安装插件进行使用 StabilityAi 开放API可以调用

6 月 13 日，Stability AI 发布了 Stable Diffusion 3 Medium（下文简称 SD3 Medium），官方声称是“迄今为止最先进的开源模型”，其性能甚至超过了 Midjourney 6。这个号称比 MJ 更牛的模型可以在民用电脑跑起来。本文简单介绍怎么才能用上这个模型~

Stability AI 公司表示 Stable Diffusion 3 Medium代表了生成式人工智能发展的一个重要里程碑，并延续了Stability AI致力于使这项强大技术民主化的承诺。SD3 Medium 可以根据用户输入的文本描述，重点克服了文生图模型中手部和脸部的挑战，生成足以乱真的的图像。

据悉，Stable Diffusion 3 Medium模型规格参数达到了20亿，可以给用户带来更真实的图片体验。目前用户可以从Hugging Face上下载该模型。

SD3 Medium 还利用其底层的 Diffusion Transformer 架构，高精度地整合了文字元素。

SD3 Medium 的另一个特点是易于使用。相比较一些资源密集型 AI 模型，SD3 Medium 可以在消费级显卡上运行，可以加速普及适配。

Stability AI 在非商业许可下提供 SD3 Medium，供免费使用。对于商业应用，可为艺术家、设计师和开发人员提供创作者许可证；对于大型商业用户，可以直接联系 Stability AI 了解授权详情。

先来看看官方给出的样张。

SD3 Medium 特点

SD3 Medium 是一个 20 亿参数的 SD3 模型，具有一些显着的功能：

• 整体质量和照片级真实感：提供具有出色细节、色彩和照明的图像，从而实现逼真的输出以及灵活风格的高质量输出。通过16通道VAE等创新，成功解决了其他型号的常见缺陷，例如手部和面部的真实感。
• 提示理解：理解涉及空间推理、构图元素、动作和风格的冗长而复杂的提示。通过使用所有三种文本编码器或组合使用，用户可以牺牲性能来换取效率。
• 排版：通过利用我们的 Diffusion Transformer 架构，实现前所未有的文本质量，减少拼写、字距调整、字母形成和间距方面的错误。
• 资源效率高：由于其 VRAM 占用空间小，非常适合在标准消费类 GPU 上运行而不会降低性能。
• 微调：能够从小型数据集中吸收细微的细节，非常适合定制。

SD3 Medium 安装

1、下载 ComfyUI 地址：

https://github.com/comfyanonymous/ComfyUI/releases

点击“Download Link with stable pytorch 2.3 cu121”下载。

下载完会得到一个“ComfyUI_windows_portable_nvidia_cu121_or_cpu.7z”文件，把它解压出来。

2、下载 stable-diffusion-3-medium 模型

https://huggingface.co/stabilityai/stable-diffusion-3-medium/tree/main

进入Hugging Face的下载页，初次下载需要填写申请单，按照小编上面红色内容填写即可，填写完成后点击[Agree and access repository] 即可通过审核，然后点击顶部的[Files and versions] 进入模型的下载页面；

框出来的几个模型都可以用，但它们的体积不一样。简单来说，体积越大的模型就越强，但也更吃性能。根据你自己的需求选模型。

3、把模型放在 ComfyUI 的模型目录里

将你下载好的模型放在 ComfyUI_windows_portable\ComfyUI\models\checkpoints 这个目录里。

4、运行 ComfyUI 画图

回到 ComfyUI 的根目录。

如果你没有N卡或者N卡配置不高，那就双击运行 run_cpu.bat 文件。

如果你有N卡就运行 run_nvidia_gpu.bat 文件。

运行后会弹出一个终端，等它运行几秒后，浏览器会自动打开 http://127.0.0.1:8188/。

试了一下 Stability 前段时间发布的样张里的提示词，用的是 sd3_medium_incl_clips.safetensors 这个模型。

anime art of a steampunk inventor in their workshop, surrounded by gears, gadgets, and steam. He is holding a blue potion and a red potion, one in each hand

对文字的理解感觉没有官方吹的那么厉害，但相比起之前的 V1.5 模型来说已经有非常明显的进步了。

5.汉化 ComfyUI 中文语言设置

最后，如果是刚开始用ComfyUI，或者英文不好的小伙伴，可以安装下面提供的汉化包，直接汉化ComfyUI，最新的Stable Diffusion 3 Medium模型同样适用！

https://github.com/AIGODLIKE/AIGODLIKE-ComfyUI-Translation

6.附Stable Diffusion 3 Medium官方分享的关键词

a female character with long, flowing hair that appears to be made of ethereal, swirling patterns resembling the Northern Lights or Aurora Borealis. The background is dominated by deep blues and purples, creating a mysterious and dramatic atmosphere. The character's face is serene, with pale skin and striking features. She wears a dark-colored outfit with subtle patterns. The overall style of the artwork is reminiscent of fantasy or supernatural genres

Digital art, portrait of an anthropomorphic roaring Tiger warrior with full armor, close up in the middle of a battle, behind him there is a banner with the text "Open Source".

photo of a dog and a cat both standing on a red box, with a blue ball in the middle with a parrot standing on top of the ball. The box has the text "SD3"

selfie photo of a wizard with long beard and purple robes, he is apparently in the middle of Tokyo. Probably taken from a phone.

A vibrant street wall covered in colorful graffiti, the centerpiece spells "SD3 MEDIUM", in a storm of colors

photo of a young woman with long, wavy brown hair tied in a bun and glasses. She has a fair complexion and is wearing subtle makeup, emphasizing her eyes and lips. She is dressed in a black top. The background appears to be an urban setting with a building facade, and the sunlight casts a warm glow on her face.

anime art of a steampunk inventor in their workshop, surrounded by gears, gadgets, and steam. He is holding a blue potion and a red potion, one in each hand

photo of picturesque scene of a road surrounded by lush green trees and shrubs. The road is wide and smooth, leading into the distance. On the right side of the road, there's a blue sports car parked with the license plate spelling "SD32B". The sky above is partly cloudy, suggesting a pleasant day. The trees have a mix of green and brown foliage. There are no people visible in the image. The overall composition is balanced, with the car serving as a focal point.

photo of young man in a black suit, white shirt, and black tie. He has a neatly styled haircut and is looking directly at the camera with a neutral expression. The background consists of a textured wall with horizontal lines. The photograph is in black and white, emphasizing contrasts and shadows. The man appears to be in his late twenties or early thirties, with fair skin and short, dark hair.

photo of a woman on the beach, shot from above. She is facing the sea, while wearing a white dress. She has long blonde hair