Depth-guided image generation with Flux
Generate a new Flux image from a prompt using the estimated depth and spatial layout of an uploaded source image.
Workflow details
Workflow details
Laufzeitprofil
- Verleger
- Sweet Tea Automation
- Status
- Aufgelistet
- Version
- Checking published version…
- Aktualisiert
- 26. Okt. 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Prompt
CLIPTextEncode
Output size
ImageScaleToTotalPixels
Extended
Additional surfaced controls
Depth adaptation
LoraLoaderModelOnly
Prompt guidance
FluxGuidance
Generation sampling
KSampler
Depth estimation sampler
KSamplerSelect
Depth estimation schedule
BasicScheduler
What you need
- Model files
- 0.3 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Sweet Tea Preview Image · image
Anforderungen
Modelle
7- Gefunden
VAE · 320 MB · SAFETENSORS · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged
- Gefunden
Text encoder · 235 MB · SAFETENSORS · Hugging Face · comfyanonymous/flux_text_encoders
flux1-depth-dev-lora.safetensors
Nicht aufgelöstLoRA · Hugging Face · Comfy-Org/flux1-dev
- Nicht aufgelöst
Checkpoint · Hugging Face · Comfy-Org/flux1-dev
lotus-depth-d-v1-1.safetensors
Datei ungeprüftCheckpoint · Hugging Face · Comfy-Org/lotus
- Datei ungeprüft
Text encoder · Hugging Face · comfyanonymous/flux_text_encoders
vae-ft-mse-840000-ema-pruned.safetensors
Datei ungeprüftVAE · Hugging Face · stabilityai/sd-vae-ft-mse-original
Knotenpakete
1- Gefunden
Knotenpaket · GitHub · tea-time-labs/sweet-tea-nodes
Quellen
1 Quelle
Quellen
1 Quelle