The core philosophy behind using Rank 512 is to move beyond simple pixel memorization. As we explored in Orakul Studio: Rank 32 learns style, Rank 128 learns technique, but Rank 512 learns the hand. This approach focuses on capturing the artist's gesture, ensuring the model learns the "hand" of the artwork rather than just copying pixels.
Showcase
1
2
3
4
5
6
7
8
9
10
🚀 Installation & Usage Guide
This release is a ready-to-use baked monolith in pure BF16 format. It is a standalone checkpoint (Merge), NOT a LoRA. To ensure the model works correctly and achieves the specified quality, strictly follow the instructions below.
📂 Where to Place the File
ComfyUI / Forge / reForge: Place the downloaded file strictly in the models/diffusion_models/ folder.
⚠️ CRITICAL: Do NOT place it in models/checkpoints/ or models/loras/.
⚙️ How to Use
In your workflow, select this file via the UNet/DiT model loading node (e.g., Load Diffusion Model in ComfyUI).
The model operates as a standalone, independent engine. No additional LoRA nodes are required to invoke this style.
🔑 Mandatory Trigger Word
Even though the style is fully integrated into the checkpoint weights, you MUST use the trigger word at the very beginning of your prompt:
PenZlTr512
💡 Technical Note: This token is the key that activates the custom rank 512 structure. Without this trigger, the model will output standard graphics and ignore the unique pencil lead texture, search lines, and custom Orakul Studio signature.
🎨 Inside the Tech: Dynamic Alpha Baking
This is the official merge of our high-ranking LoRA directly into the base checkpoint. Using a custom protocol with dynamic alpha, we were able to bake a live pencil texture without destroying the geometry.
This version is designed for those who want a refined, soft graphite stroke (HB/2B) with perfect airy shading, completely eliminating the heavy "marker" burnout and inky blackness.
⚠️ Strict Generation Rules
To ensure the model delivers the advertised analog quality and a soft gray tone, use only these settings:
json
1| Parameter | Optimal Value | Description |
2| :--- | :--- | :--- |
3| **Sampling Steps** | `20` | *Strictly 20. No more, no less. This is the ideal diffusion point, where the dark fractions don't have time to turn into a dull ink.* |
4| **CFG Scale** | `2.5` | *Critically important! Don't set it higher—it will burn the midtones.* |
5| **Sampler** | `UniPC` | *Recommended by the author for perfect line accuracy.* |
6| **Scheduler** | `G Uniform` | *Ensures a soft noise distribution.* |
7| **Denoise** | `0.95` | *Optimal balance for revealing hidden graphics layers.* |
89---
1011### 🌐 Official Repository
12For updates and core development info, follow us on GitHub:13👉 **[Orakul Studio GitHub](https://github.com/OrakulStudio)**141516---
1718## 📄 Citation
1920```json
21@article{team2025zimage,22 title={Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer},23 author={Z-Image Team},24 journal={arXiv preprint arXiv:2511.22699},25 year={2025}26}
