Anima depth-guided illustration
Upload a reference image with the spatial layout you want to guide, then describe the new scene and style in the positive prompt. The reference is resized, Depth Anything 3 estimates its depth, and Anima generates a fresh image using that depth as guidance. Outputs include the generated image batch and the grayscale depth preview.
Workflow details
Workflow details
Profil d'exécution
- Éditeur
- Sweet Tea Automation
- Statut
- Présenté
- Version
- Checking published version…
- Mis à jour
- 25 oct. 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Source image
LoadImage
Positive prompt
CLIPTextEncode
Negative prompt
CLIPTextEncode
Output size
ResizeImageMaskNode
Depth guidance
AnimaLLLiteApply
Turbo mode
PrimitiveBoolean
Extended
Additional surfaced controls
Image count
EmptyLatentImage
Sampling
KSampler
Standard steps
PrimitiveInt
Standard guidance
PrimitiveFloat
Turbo steps
PrimitiveInt
Turbo guidance
PrimitiveFloat
Turbo LoRA
LoraLoaderModelOnly
Depth estimation
DA3Inference
Depth map
DA3Render
What you need
Hardware and download-size estimates are not available yet.
Outputs
- Generated illustrations · image
- Depth guidance preview · image
Exigences
Modèles
6- Fichier non vérifié
Checkpoint · Hugging Face · circlestone-labs/Anima
anima-lllite-depth-1.safetensors
Fichier non vérifiéCheckpoint · Hugging Face · Comfy-Org/Anima-LLLite
LoRA · 142 MB · SAFETENSOR · Hugging Face · circlestone-labs/Anima-Official-LoRAs
depth_anything_3_mono_large.safetensors
Fichier non vérifiéCheckpoint · Hugging Face · Comfy-Org/Depth-Anything-3
- Fichier non vérifié
Text encoder · Hugging Face · circlestone-labs/Anima
- Fichier non vérifié
VAE · Hugging Face · circlestone-labs/Anima
Packs de nœuds
1Pack de nœud · GitHub · tea-time-labs/sweet-tea-nodes
Sources
1 source
Sources
1 source