Description:

This workflow allows you to generate images from text inspired by an existing image. It is optimized to integrate all metadata for simplified online publishing.
It integrates an upscaler/sampler which, although it takes longer than a classic upscaler, allows for much better quality.

Resources you need:

📂Files :

For base version
Model : fp8, bf16
in models\diffusion_models

CLIP : qwen_2.5_vl_7b_fp8_scaled.safetensors
in models\clip

For GGUF version
Model : Q8, Q5, Q4
in models\unet

CLIP : Q8, Q6, Q5, Q4, Q3
in models\clip

Common files

VAE : qwen_image_vae.safetensors
in models\vae

LoRA : Qwen-Image-Lightning-8steps-V2.0.safetensors or Qwen-Image-Lightning-4steps-V2.0.safetensors
in models\loras

📦Custom Nodes :

• ComfyUI-GGUF

• rgthree-comfy

• ComfyUI-KJNodes

• ComfyUI-mxToolkit

• ComfyUI Image Saver

• ComfyUI-Easy-Use

• ComfyUI_UltimateSDUpscale

• VRGameDevGirl Video Enhancement Nodes