Description:
This workflow allows you to generate images from text inspired by an existing image using a ControlNet processor. It is optimized to integrate all metadata for simplified online publishing.
You will find a step-by-step guide to using this workflow here: link
For examples and explanations of ControlNet I recommend this article : How to use ControlNet with SDXL model - Stable Diffusion Art
Resources you need:
📂Files for "base" version :
Depth : flux1-depth-dev-fp8.safetensors or flux1-depth-dev-fp16.safetensors
in ComfyUI\models\diffusion_models
Canny : flux1-canny-dev-fp8.safetensors or flux1-canny-dev-fp16.safetensors
in ComfyUI\models\diffusion_models
Model : flux1-dev-fp8.safetensors
in ComfyUI\models\diffusion_models
CLIP : t5xxl_fp8_e4m3fn.safetensors
in ComfyUI\models\clip
Text encoder : ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors or clip_l.safetensors
VAE : ae.safetensors
in ComfyUI\models\vae
📂Files for GGUF version :
Depth : Q8,Q5,Q4
in ComfyUI\models\unet
Canny : Q8,Q5,Q4
in ComfyUI\models\unet
Model : Q8, Q6, Q5, Q4, Q3
in ComfyUI\models\unet
CLIP : Q8, Q6, Q5, Q4, Q3
in ComfyUI\models\clip
Text encoder : ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors or clip_l.safetensors
in ComfyUI\models\clip
VAE : ae.safetensors
in ComfyUI\models\vae
ANY upscale model :
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in ComfyUI\models\upscale_models
Controlnet (for v5 and earlier)
Canny: flux-canny-controlnet-v3.safetensors
Depth: flux-depth-controlnet-v3.safetensors
Hed: flux-hed-controlnet-v3.safetensors
https://huggingface.co/XLabs-AI/flux-controlnet-hed-v3/blob/main/flux-hed-controlnet-v3.safetensors
in \ComfyUI\models\xlabs\controlnets
Custom Nodes :
Description
TorchCompile include for beter speed,
easy activator for upscaling,
simple backend for better compatibility.