Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Generate new images from a prompt while following edges extracted from a reference image. Outputs include the generated image batch and one reference edge-map preview.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Reference image
LoadImage
Image prompt
CLIPTextEncode
Output size
EmptySD3LatentImage
Edge guidance
ControlNetApplyAdvanced
Extended
Additional surfaced controls
Reference resizing
ImageScale
Edge detection
Canny
Sampling
KSampler
Hardware and download-size estimates are not available yet.
Requirements
sd3.5_large_controlnet_canny.safetensors
File unverifiedControlNet · Hugging Face · Comfy-Org/stable-diffusion-3.5-controlnets_ComfyUI_repackaged
sd3.5_large_fp8_scaled.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/stable-diffusion-3.5-fp8 · Stable Diffusion 3.5 FP8
Node pack · GitHub · tea-time-labs/sweet-tea-nodes
