Anima ControlNet VACE Depth
circlestone-labs-non-commercial-license
Source du modèle
- Type
- Other
- Taille du fichier
- 568 MB
- Modèle de base
- Anima-Base-V1.0
- Version
- vRevision 4ffaa3c
- Mis à jour
- 7 oct. 2026
- Téléchargements
- 0
- Source
- Hugging Face
Description de la source
Anima-ControlNet-VACE-Depth
A depth ControlNet for Anima, trained with the VACE spaced-block-duplication + zero-conv architecture.
⚠️ This release contains adapter weights only. It is not a standalone model — you must load it together with the Anima base model.
Training
Trained with sd-scripts by kohya-ss
| Setting | Value |
|---|---|
| Base Model | Anima-Base-V1.0 |
| Optimizer | AdamW (fp32 states), weight decay 0.01 |
| Learning rate | 5e-5, cosine, 500-step warmup |
| Effective batch | 16 |
| Steps | 20,000 |
| Resolution | 10242 |
| Precision | bf16 (full_bf16) |
| Flow shift | 5.0 (matches inference) |
| Loss | L2 on flow-matching velocity |
| Weighting | uniform |
Tips
- Depth source: Use DepthAnything V2 for best performance, although this model is trained on a mix of different depth sources, and thus any popular depth preprocessor should in theory work.
Usage
Supported for the moment in ComfyUI through my fork of ComfyUI-Advanced-ControlNet
Credits
- Anima - Circlestone Labs
- sd-scripts — kohya-ss.
Sources
1 source
Sources
1 sourceVérifié 7 oct.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactanima-vace-depth.safetensors
safetensors · 568 MB · SHA-256 29762e7037bd…802d · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: other license_name: circlestone-labs-non-commercial-license base_model: Anima-Base-V1.0 tags: - text-to-image - controlnet - depth - anima pipeline_tag: text-to-image --- # Anima-ControlNet-VACE-Depth A **depth ControlNet** for **Anima**, trained with the **VACE** spaced-block-duplication + zero-conv architecture. > ⚠️ **This release contains adapter weights only.** It is not a standalone > model — you must load it together with the Anima base > model. --- ## Training Trained with sd-scripts by kohya-ss | Setting | Value | |---|---| | Base Model | Anima-Base-V1.0 | | Optimizer | AdamW (fp32 states), weight decay 0.01 | | Learning rate | 5e-5, cosine, 500-step warmup | | Effective batch | 16 | | Steps | 20,000 | | Resolution | 1024² | | Precision | bf16 (full_bf16) | | Flow shift | 5.0 (matches inference) | | Loss | L2 on flow-matching velocity | | Weighting | uniform | ## Tips - **Depth source**: Use DepthAnything V2 for best performance, although this model is trained on a mix of different depth sources, and thus any popular depth preprocessor should in theory work. ## Usage Supported for the moment in ComfyUI through my fork of [ComfyUI-Advanced-ControlNet](https://github.com/TaihoC/ComfyUI-Advanced-ControlNet-Anima/tree/feat/anima-vace-controlnet) ## Credits - **Anima** - Circlestone Labs - **sd-scripts** — kohya-ss.
Source context: 0 downloads · 16 likes · Pipeline text-to-image · Repo TaihoC/Anima-ControlNet-VACE-Depth
Source context: 0 downloads · 12 likes · Pipeline text-to-image · Repo TaihoC/Anima-ControlNet-VACE-Depth
