# 概览

在 CLORE.AI GPU 上使用 AI 模型生成图像。

## 工具与界面

| 工具                                                                                            | 描述                      | 难度 |
| --------------------------------------------------------------------------------------------- | ----------------------- | -- |
| [FLUX.1](/guides/guides_v2-zh/tu-xiang-sheng-cheng/flux.md)                                   | 最佳质量，文本渲染               | 中等 |
| [FLUX.2 Klein](/guides/guides_v2-zh/tu-xiang-sheng-cheng/flux2-klein.md)                      | 亚秒级图像生成                 | 中等 |
| [Stable Diffusion WebUI](/guides/guides_v2-zh/tu-xiang-sheng-cheng/stable-diffusion-webui.md) | 功能丰富的经典界面               | 简单 |
| [Stable Diffusion WebUI Forge](/guides/guides_v2-zh/tu-xiang-sheng-cheng/sd-webui-forge.md)   | 优化的 WebUI 变体            | 简单 |
| [Stable Diffusion 3.5](/guides/guides_v2-zh/tu-xiang-sheng-cheng/stable-diffusion-3-5.md)     | 最先进的开源模型                | 中等 |
| [ComfyUI](/guides/guides_v2-zh/tu-xiang-sheng-cheng/comfyui.md)                               | 基于节点的工作流程               | 中等 |
| [Fooocus](/guides/guides_v2-zh/tu-xiang-sheng-cheng/fooocus-simple-sd.md)                     | 简易的 Stable Diffusion 界面 | 简单 |
| [InvokeAI](/guides/guides_v2-zh/tu-xiang-sheng-cheng/invokeai.md)                             | 专业图像生成界面                | 中等 |
| [PixArt](/guides/guides_v2-zh/tu-xiang-sheng-cheng/pixart-image-gen.md)                       | 基于 DiT 的快速生成            | 中等 |
| [混元图像 3.0](/guides/guides_v2-zh/tu-xiang-sheng-cheng/hunyuan-image3.md)                       | 统一的生成与编辑                | 中等 |
| [SDXL Turbo 与 LCM](/guides/guides_v2-zh/tu-xiang-sheng-cheng/sdxl-turbo.md)                   | 快速推理模型                  | 简单 |

## GPU 推荐

| 模型     | 最低显存 | 推荐    |
| ------ | ---- | ----- |
| SD 1.5 | 4GB  | 8GB+  |
| SDXL   | 8GB  | 12GB+ |
| FLUX.1 | 12GB | 24GB+ |
| SD 3.5 | 16GB | 24GB+ |

## 提示

* 使用 **竞价（Spot）** 批量生成的订单
* 启用 xFormers/Flash Attention 以加速
* 先从较小的模型开始测试提示词

## 相关指南

* [图像处理](/guides/guides_v2-zh/tu-xiang-chu-li/image-processing.md) - 放大，修复
* [ControlNet](/guides/guides_v2-zh/tu-xiang-chu-li/controlnet-advanced.md) - 引导式生成
* [训练](/guides/guides_v2-zh/xun-lian/training.md) - 训练自定义模型


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.clore.ai/guides/guides_v2-zh/tu-xiang-sheng-cheng/image-generation.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.