WorkflowListedExternal

Mode [Flux,SD3,SDXL,AURA,HYD,SD1,SC] — 0.0

SD1、SDXL、SD3、FLUX、AURAFLOW、HUNYUANDIT和eh Stable Cascade。您需要更新选择器节点它们在ComfyOrg注册表中,而不是在CivitAI上) 。 Dev不会检测到Schnell。

Sourcecivitai.com/models/1613297

TaskMultiCapabilitiesImage to image · Text to image · UpscalingFamilyFLUXEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Sep 13, 2026

Source description

系统根据模型通过5个特别优化的工作流程自动重新路由。编写prompt并加载模型。点击播放。就是这样。

SD1、SDXL、SD3、FLUX、AURAFLOW、HUNYUANDIT和~eh Stable Cascade。您需要更新选择器节点 https://github.com/exdysa/comfyui-selector( 它们在ComfyOrg注册表中,而不是在CivitAI上) 。 Dev不会检测到Schnell。

模块化绿松石组可以拖动,方便重新路由和诊断。采样器输入是彩色编码的。调度器、求解器和方向可以洗牌与模型兼容的设置。OLLAMA LLM prompt。输出端口已准备好进行升级和细节化。

注意:这个项目已经被放弃。

有人告诉我,像这样自动化ComfyUI是不可能的。不,但ComfyUI不适用于复杂的应用程序。超过300个节点填满了屏幕。系统跟不上。自动切换极难测试。这是不可持续的,但它可能会提供信息、动力和教育。探索ComfyUI的局限性。

没有支持。我不知道它是否还能用。我不在乎。我现在在用扩散器。请期待它。

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

Use this ComfyUI workflow to generate images from a written prompt and a loaded model; it routes processing through five workflows, saves images, and provides an output prepared for upscaling and detailing.

Flow

Enter a prompt, load a model, and click Play.
The selected model routes processing through five workflows, and the modular turquoise group can be dragged to change routing or help diagnose the setup.

Inputs and outputs

The workflow names SD1, SDXL, SD3, FLUX, AURAFLOW, HUNYUANDIT, and Stable Cascade as model families.
It includes VAEDecode and SaveImage nodes, with an output port prepared for upscaling and detailing.

Setup

Before use, update the selector node using https://github.com/exdysa/comfyui-selector; the selectors are in the ComfyOrg registry rather than on CivitAI.
Suggestion · not verified

Dependencies

Named model files include: 4x_foolhardy_Remacri.pth; ae.safetensors; auraflow.vae.diffusers.safetensors; clip__gmodel.safetensors; clip_g.sd35.safetensors; clip_l.flux.safetensors; clip_l.sd35.safetensors; flatpiecexlVAE_baseonA1579.safetensors; Long-ViT-L-14-BEST-GmP-smooth-ft.s
Named workflow components include: ImageUpscaleWithModel; CheckpointLoaderSimple; UNETLoader; MathExpression|pysssss; PerpNegGuider; SelInGuider; LoadImage; RecourseImage; SaveImage; DualCLIPLoader; ConditioningZeroOut; SamplerCustom; KSamplerSelect; RecoursePolar; RandomNoise.
Additional named components include: ModelSamplingFlux; SamplerEulerAncestral; ModelSamplingAuraFlow; ModelSamplingSD3; PerturbedAttentionGuidance; SelInSampler; LatentUpscaleBy; AlignYourStepsScheduler; ImpactSchedulerAdapter; ShowText|pysssss; SelInPolar; SelInInt; CLIPText； CL

Configuration

The sampler input is color-coded.
Schedulers, solvers, and orientation can be shuffled among model-compatible settings.
The workflow includes an OLLAMA LLM prompt.

Cautions

The project is described as abandoned and without support; whether it can still be used is unknown, and Schnell will not be detected from Dev.
Before relying on it, verify that your ComfyUI setup includes the named model files and workflow components, and confirm which ae.safetensors file to use.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/1613297

Verified Jul 19

Source excerpts

1 excerpt

NoteJul 19civitai.com/models/1613297

Source context: 110 downloads · Type Workflows · Base model Flux.1 S