Sign In

Palladium

Download

1 variant available

bf16 SafeTensor

ArsFulmina.safetensors_00001_.safetensors

BF16, good balance • 3.9 GB

Verified:

Type
Checkpoint
Stats

174

Reviews
Published

Jul 14, 2026

Base Model

Anima

Hash
AutoV2
3D0A25D3C4
default creator card background decoration
Uploads - 275

275

Followers - 1877

1.9K

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. 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

2026-07-14-010407_184265022870288_Upscale.png

🌠 Palladium [Anime Model Merge]

⚗️ A radiant fusion of precision, saturation, and control.

Palladium stands as a refined evolution of the Illustrious foundation — a model designed to generate colorful, expressive anime imagery with excellent prompt fidelity, balanced lighting, and natural contrast.

This version integrates utopiaOptimizedVAE (baked-in) for enhanced detail, smoother tonal transitions, and optimal performance under low CFG and step counts, maintaining clarity without sacrificing richness.


🧬 Model Overview

FeatureDescription🧠 BaseIllustrious merge🧩 VAEutopiaOptimizedVAE (baked-in)⚙️ Step Range20 – 35🎚️ CFG Range (Tested)3.0 – 3.5💫 Recommended SchedulerRes_Multistep (Beta)🧭 Compatible SamplersEuler, Euler a, DPM++, etc.🎨 StyleColor-rich anime, balanced contrast, strong composition🔍 StrengthsPrompt adherence, saturation balance, multi-scene versatility


🌈 Visual Traits

Vivid Color Expression – Deep saturation and clean gradients without oversaturation.
🎭 Prompt-Faithful Generation – Consistent response to descriptive and stylistic prompts.
🌤️ Dynamic Contrast – Smooth lighting, lively shadows, and defined depth.
🖌️ Adaptable Aesthetics – Performs well across characters, scenery, and concept compositions.


🧠 Steps: 20–35
🎚️ CFG: 3.0–3.5
💡 Scheduler: Res_Multistep (Beta) + Euler/Euler a recommended

💬 Lower CFGs maintain detail and natural tone due to baked VAE optimization.


1024x1024  
1152x896 | 896x1152  
1216x832 | 832x1216  
1344x768 | 768x1344  
1536x640 | 640x1536

🧩 Models from merge will be listed under suggested resources


💬 Notes

  • Ideal for anime portraits, dynamic lighting, and artistic compositions.

  • Works well in colorful storytelling environments or stylized concept scenes.

  • Balanced to perform effectively in general-purpose anime workflows.