Generate a prompted SD3.5 Large image guided by depth estimated from a source image. Provide a source image and describe the image to generate. Output size retains the source aspect ratio at the selected megapixel budget. Depth guidance controls its strength and the portion of generation during which it applies. Advanced controls tune generation, randomization and Lotus depth estimation. The inverted depth map supplies both ControlNet guidance and the initial generation latent; lowering Denoise retains more of that depth-map initialization. Negative conditioning is zeroed automatically, so there is no separate negative prompt. The output is the final generated image.
Workflow details
Quellen
1 QuelleLaufzeitprofil
Hover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Positive prompt
CLIPTextEncode
Output size
ImageScaleToTotalPixels
Depth guidance
ControlNetApplyAdvanced
Extended
Additional surfaced controls
Sampling
KSampler
Depth estimation sampler
KSamplerSelect
Depth estimation sampling
BasicScheduler
Hardware and download-size estimates are not available yet.
Anforderungen
lotus-depth-d-v1-1.safetensors
Datei ungeprüftCheckpoint · Hugging Face · Comfy-Org/lotus
sd3.5_large_controlnet_depth.safetensors
Nicht aufgelöstControlNet · Hugging Face · Comfy-Org/stable-diffusion-3.5-controlnets_ComfyUI_repackaged
sd3.5_large_fp8_scaled.safetensors
Datei ungeprüftCheckpoint · Hugging Face · Comfy-Org/stable-diffusion-3.5-fp8 · Stable Diffusion 3.5 FP8
vae-ft-mse-840000-ema-pruned.safetensors
Datei ungeprüftVAE · Hugging Face · stabilityai/sd-vae-ft-mse-original
Knotenpaket · GitHub · tea-time-labs/sweet-tea-nodes