InvokeAI
Professional creative engine with a unified canvas for Stable Diffusion and FLUX.
- Star 数
- 28.6K
- Fork 数
- 3.1K
- 未关闭 Issue
- 440
- 最近提交
- 2026-10-15
数据来自 GitHub API · 更新于 2026-10-15
InvokeAI 是什么？
InvokeAI pairs a polished web UI with a layer-based canvas for inpainting, outpainting, regional prompting and control layers. It manages models for you, supports SD1.5, SDXL and FLUX, and includes a node workflow editor for advanced users.
主要功能
- Unified canvas with layers, masks and regional guidance
- Model manager with one-click starter models
- Node-based workflow editor
- Board-based gallery for organizing outputs
系统要求
- 平台
- Windows · macOS · Linux · Docker
- 显卡
- NVIDIA (CUDA), AMD (ROCm, Linux) or Apple Silicon
- 显存
- 4 GB for SD1.5, 8 GB for SDXL, 10 GB+ for FLUX
- 内存
- 16 GB+ (32 GB for FLUX)
如何安装 InvokeAI
根据项目 README 整理。开源项目更新很快，请以 GitHub 页面上的最新说明为准。
Launcher (Windows / macOS / Linux)
- 1Download the Invoke Community Edition launcher from the official downloads page.
- 2Run the launcher, choose an install folder and GPU type, and click Install.
- 3Launch Invoke and add starter models from the Model Manager.
Docker (NVIDIA)
- 1Run the official image and open http://localhost:9090.
docker run --runtime=nvidia --gpus=all --publish 9090:9090 ghcr.io/invoke-ai/invokeai
优势
- Best canvas/inpainting UX
- Clean, stable UI
- Permissive license
不足
- Fewer community extensions than ComfyUI
- New models arrive later than in ComfyUI
InvokeAI 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| InvokeAI Professional creative engine with a unified canvas for Stable Diffusion and FLUX. | 28.6K | Apache-2.0 | 4 GB for SD1.5, 8 GB for SDXL, 10 GB+ for FLUX | |
| ComfyUI Node-based interface for diffusion models — images, video and audio. | 137.6K | GPL-3.0 | 4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models | |
| Krita AI Diffusion Generate and inpaint inside the Krita painting app. | 10.7K | GPL-3.0 | — | |
| Fooocus Midjourney-like simplicity for SDXL: type a prompt and press Generate. | 53.4K | GPL-3.0 | 4 GB minimum, 6 GB+ recommended | |
| Stable Diffusion WebUI Forge A faster, leaner fork of the A1111 WebUI with FLUX support. | 13.1K | AGPL-3.0 | 6 GB+ (FLUX NF4/GGUF variants run on 6–8 GB) | |
| Stable Diffusion WebUI (AUTOMATIC1111) The classic browser UI for Stable Diffusion with a massive extension ecosystem. | 165.1K | AGPL-3.0 | 4 GB minimum (with --medvram/--lowvram), 8 GB+ recommended |
相关模型
常见问题
InvokeAI 免费吗？
是的——InvokeAI 是开源软件，采用 Apache-2.0 许可证。商用前请确认软件及模型权重的许可条款。
InvokeAI 支持 Windows、Mac 和 Linux 吗？
InvokeAI 支持：Windows, macOS, Linux, Docker。
运行 InvokeAI 需要什么配置？
NVIDIA (CUDA), AMD (ROCm, Linux) or Apple Silicon. VRAM: 4 GB for SD1.5, 8 GB for SDXL, 10 GB+ for FLUX. RAM: 16 GB+ (32 GB for FLUX)
如何安装 InvokeAI？
1. Download the Invoke Community Edition launcher from the official downloads page. 2. Run the launcher, choose an install folder and GPU type, and click Install. 3. Launch Invoke and add starter models from the Model Manager.
InvokeAI 有哪些好的替代品？
常见替代品包括 ComfyUI, Krita AI Diffusion, Fooocus, Stable Diffusion WebUI Forge，详见本页对比表。
可以不安装、在线使用 InvokeAI 吗？
如果只想要结果，AiLoft 可在浏览器中运行 GPT Image 2.5、Nano Banana Pro 等顶级图像模型，无需显卡和配置。
不想安装？直接在浏览器里生成图片
无需显卡、驱动或 Python。在线使用 GPT Image 2.5 和 Nano Banana Pro，并排对比效果。