Description:
This workflow allows you to generate images from another images. It is optimized to integrate all metadata for simplified online publishing.
Resources you need:
📂Files :
For base version
Model : fp8 or bf16
in models\diffusion_models
For GGUF version
Model : Q8,Q6,Q5,Q4,Q3
in models\unet
VAE : qwen_image_vae.safetensors
in models\vae
CLIP : qwen_2.5_vl_7b_fp8_scaled.safetensors
in models\clip
LoRA : 8steps, 4steps
in models\loras
📦Custom Nodes :
Description
Tested on ComfyUI v0.3.62.
A few modifications to standardize my workflows.
Change to QWEN Edit 2509.
Up to 3 base images.
FAQ
Comments (2)
Thank you, for update.
I notice an issue with disabling image 3. You need to disable "Scale image 3" in the same time. If not you've got an error.
I am having an issue, where if I turn off the 2 extra images, so I am only working with 1 image. When I hit run, i get this failure
Prompt execution failed Prompt outputs failed validation: ImageScaleToTotalPixels: - Required input is missing: image ImageScaleToTotalPixels: - Required input is missing: image
The imagescale nodes don't turn off despite the larger image loaders being bypassed.
Now I need to learn how to fix this bypass stuff.