Hugging Face's logo

khanghy1000
/
Anima-ControlNet-VACE-Canny

Text-to-Image
Diffusion Single File
controlnet
canny
anima
comfyui
Model card Files
xet
 Community
Anima-ControlNet-VACE-Canny / README.md
khanghy1000's picture
khanghy1000
Upload v1
8f76d95 unverified
preview code
|
Raw
History Blame Contribute Delete
2.21 kB
metadata 
license: other
license_name: circlestone-labs-non-commercial-license
license_link: LICENSE.md
base_model:
  - circlestone-labs/Anima
base_model_relation: adapter
tags:
  - controlnet
  - canny
  - anima
  - text-to-image
  - diffusion-single-file
  - comfyui
datasets:
  - RicemanT/booru-essence-2026

Anima-ControlNet-VACE-Canny

A Canny ControlNet for Anima, trained with Anima VACE ControlNet implementation by TaihoC.

⚠️ Requires the fix/anima-vace-hardening branch of PineCookie/ComfyUI-Advanced-ControlNet. (TaihoC's fork currently has a duplicate control hook bug.)

preview

Training Details

Dataset

  • Dataset: ~15,000 Danbooru images from RicemanT/booru-essence-2026.
  • Canny Edge Maps: Generated using cv2.Canny with min_threshold=100 and max_threshold=200 (no random thresholds).
  • Caption Dropout: 10%.

Hyperparameters

  • Control Blocks: 4 control blocks, connected to the base model at blocks 0, 7, 14, and 21.
  • Batch Size: 16 (GPU: 2, Gradient Accumulation: 8)
  • Training Steps: 3000
  • Learning Rate: 5e-5, cosine, 150 warmup steps
  • Optimizer: AdamW_adv
    • betas: (0.9, 0.99)
    • use_atan2: True
    • orthogonal_gradient: iterative
    • state_precision: bf16_sr
    • stochastic_rounding: True
  • Training Precision: full bf16
  • Timestep Sampling: shift, discrete_flow_shift=3.0, sigmoid_scale=1.0
  • Resolution: 1024x1024

Peak VRAM Usage: ~32GB (no gradient checkpointing)

Compute Cost: ~10 hours on 1x L40S

Credits