Turn a source image into a batch of generated layer images, guided by an overall image description. Upload your image and replace the example description “guitar” with a description of its objects, appearance and arrangement, including relevant partly occluded elements. The description guides the whole decomposition; there are no individual layer prompts or controls assigning objects to particular layers.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Image description
CLIPTextEncode
Input resolution
ImageScaleToMaxDimension
Layer count and batch
EmptyQwenImageLayeredLatentImage
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Sampling
KSampler
Sampling shift
ModelSamplingAuraFlow
Hardware and download-size estimates are not available yet.
Requirements
qwen_2.5_vl_7b_fp8_scaled.safetensors
Not resolvedText encoder · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged
qwen_image_layered_control_bf16.safetensors
File unverifiedCheckpoint · Hugging Face · DiffSynth-Studio/Qwen-Image-Layered-Control
qwen_image_layered_vae.safetensors
File unverifiedVAE · Hugging Face · Comfy-Org/Qwen-Image-Layered_ComfyUI
Node pack · GitHub · tea-time-labs/sweet-tea-nodes