Qwen-Image depth-guided creation
Generate a prompted Qwen-Image result using the depth structure of an uploaded reference, and receive a preview of the depth map used for guidance.
Workflow details
Workflow details
Runtime profile
- Publisher
- Sweet Tea Automation
- Status
- Listed
- Version
- Checking published version…
- Updated
- Oct 26, 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Positive prompt
CLIPTextEncode
Depth guidance
ControlNetApplyAdvanced
Generation
KSampler
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Lightning acceleration
LoraLoaderModelOnly
Depth estimation
SetFirstSigma
Sampling shift
ModelSamplingAuraFlow
Depth sampler
KSamplerSelect
Depth sampling
BasicScheduler
What you need
Hardware and download-size estimates are not available yet.
Outputs
- Generated image · image
- Depth-map preview · image
Requirements
Models
7lotus-depth-d-v1-1.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/lotus
qwen_2.5_vl_7b_fp8_scaled.safetensors
File unverifiedText encoder · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
qwen_image_fp8_e4m3fn.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
- File unverified
VAE · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
Qwen-Image-InstantX-ControlNet-Union.safetensors
File unverifiedControlNet · Hugging Face · Comfy-Org/Qwen-Image-InstantX-ControlNets
Qwen-Image-Lightning-4steps-V1.0.safetensors
File unverifiedLoRA · Hugging Face · lightx2v/Qwen-Image-Lightning
vae-ft-mse-840000-ema-pruned.safetensors
File unverifiedVAE · Hugging Face · stabilityai/sd-vae-ft-mse-original
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source