UmeAiRT ComfyUI auto installer

I'm sharing with you my installation script, which automatically provides ComfyUI, workflows, FLUX model, ...

With a few questions at the beginning of the script, only the desired elements will be downloaded.

Prerequisites :

• CUDA 12.9

What's included :

ComfyUI :

• portable version pytorch 2.8.0+cu129,

• ComfyUI Manager,

• all custom nodes used in my workflows.

Workflow :

• TXT to IMG.json: Basic text-to-image generation.

• IMG to IMG.json: Basic image-to-image generation.

• INPAINT.json: For modifying or replacing part of an image (inpainting).

• OUTPAINT.json: For extending an image beyond its original borders (outpainting).

• KONTEXT.json: For contextual editing and generation.

• ControlNet

  • CtrlNet Canny.json: Guides generation using Canny edges.

  • CtrlNet Depth.json: Guides generation using a depth map.

  • CtrlNet HED.json: Guides generation using soft edges (HED).

  • CtrlNet Openpose.json: Guides generation from a skeletal pose.

• Tools

  • LoRA.json: Example of how to use a LoRA with FLUX models.

  • Upscale.json

Models : (base,gguf,nunchaku)

• Flux1-dev,

• Flux1-fill,

• Flux1-Kontext.

Clips :

• ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF,

• Clip_l,

• t5xxl_fp8_e4m3fn.safetensors.

ControlNet :

• Canny,

• Depth,

• Hed,

• OpenPose.

Upscale Model :

• RealESRGAN_x4plus.pth

• RealESRGAN_x4plus_anime_6B.pth

Custom Nodes included :

• ComfyUI-Custom-Scripts

• ComfyUI-GGUF

• ComfyUI-KJNodes

• ComfyUI-VideoHelperSuite

• ComfyUI-mxToolkit

• ComfyUI-HunyuanVideoMultiLora

• rgthree-comfy

• ComfyUI-Frame-Interpolation

• ComfyUI Impact Pack

• ComfyUI-Easy-Use

• WAS Node Suite

• ComfyUI-Florence2

• ComfyUI-Upscaler-Tensorrt

• ComfyUI-MultiGPU

• ComfyUI-WanStartEndFramesNative

• comfyui_controlnet_aux