Sign In

ZodaMix šŸ¶

445

Updated: Jul 31, 2026

base modelanima

Not recently loaded

Download

1 variant available

fp16 SafeTensor

ZodaMix.safetensors

Half precision, best balance • 3.9 GB

Verified:

You need these files to run this model. We'll show the best match for your preferences.

Text Encoder

qwen_3_06b_base.safetensors • 1.11 GB

Verified:

Qwen Image VAE • qwen_image_vae.safetensors

242.05 MB

Downloads your preferred variants

Type
Checkpoint Merge
Stats

1,490

445

3.9K

Reviews
Published

Jun 23, 2026

Base Model
Training
Steps: 3,000Epochs: 30
Usage Tips
Clip Skip: 2
Hash
AutoV22363930C02

The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos


ļ¼ļ¼ļ¼ ZodaMix šŸ¶ best buddy of ZodaPlus šŸ¾ ļ¼ļ¼ļ¼

Core Features & Design Focus

Enhanced Detail Rendering: Delivers sharper linework, crisper facial features, and richer background textures out of the box without requiring heavy post-processing.

Model Synergy & Coordination: Specifically engineered to eliminate style conflicts and anatomical artifacts common in mixed checkpoints, ensuring stable compositions and smooth blending between layered models.

Zoda Plus Optimization: Tailored to complement the Zoda Plus ecosystem. When paired with Zoda Plus models or adapters, it unlocks enhanced color vibrancy, superior lighting, and peak structural stability.

Stylized Focus: Built strictly for anime, digital illustration, and non-photorealistic artwork (not intended for realism).


CFG Scale: 4.0 – 7.0 (Adjust based on prompt strength)

Steps: 24 – 50 (Default: 35. Higher steps are recommended if you are skipping high-res fix/upscaling)

Sampler: er_sde

Scheduler: Simple


Installation Paths (ComfyUI)

Model Checkpoint (zodamix_anima10.safetensors) → ComfyUI/models/diffusion_models (or Stable-diffusion)

Pair with your preferred text encoders and VAE files in their respective directories.


Resources:

I also provide comfyUI workflow blow.

Zoda Plus Synergy: Activate ZodaPlus to fully leverage the model's specialized coordination tuning.