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 and an already preprocessed blur reference using SD3.5 Large and its blur ControlNet. Upload the required reference and describe the desired subject, appearance, materials, and details in the positive prompt. This tool does not blur or otherwise preprocess the upload.
Workflow details
Runtime profile
Sources
1 sourceHover nodes for Pipe controls
Core
Primary Pipe surface
Blur reference
LoadImage
Positive prompt
CLIPTextEncode
Output size
EmptySD3LatentImage
Reference guidance
ControlNetApplyAdvanced
Extended
Additional surfaced controls
Sampling
KSampler
Hardware and download-size estimates are not available yet.
Requirements
sd3.5_large_controlnet_blur.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
