SD3.5 Large blur-guided image generation
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
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
Blur reference
LoadImage
Positive prompt
CLIPTextEncode
Output size
EmptySD3LatentImage
Reference guidance
ControlNetApplyAdvanced
Extended
Additional surfaced controls
Sampling
KSampler
What you need
Hardware and download-size estimates are not available yet.
Output
- Sweet Tea Preview Image · image
Requirements
Models
2ControlNet · 8.06 GB · SAFETENSORS · Hugging Face · Comfy-Org/stable-diffusion-3.5-controlnets_ComfyUI_repackaged
Checkpoint · 13.9 GB · SAFETENSORS · Hugging Face · Comfy-Org/stable-diffusion-3.5-fp8
Node packs
1Node pack · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source