VoidMix-Atmospheric / README.md
voidwayy's picture
Update README.md
ca614e5 verified
|
Raw
History Blame Contribute Delete
3.8 kB
---
license: other
license_name: fair-ai-public-license-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
base_model:
- OnomaAIResearch/Illustrious-xl-early-release-v0
pipeline_tag: text-to-image
tags:
- illustrious
- bloom
- volumetrics
- atmospheric
- clean
- detailed
- hyperdetailed
- absurdres
- detailer
- vibrant
- balanced
- sdxl
- stable-diffusion-xl
- comfyui
- image-generation
---
<div align="center">
# 🌌 VoidMIX
<div style="display: flex; gap: 8px; justify-content: center; flex-wrap: wrap; margin: 10px 0 20px 0;">
<span style="background: rgba(147, 51, 234, 0.12); color: #9333ea; border: 1px solid rgba(147, 51, 234, 0.3); padding: 4px 14px; border-radius: 9999px; font-size: 0.85em; font-weight: 600;">SDXL Checkpoint</span>
<span style="background: rgba(59, 130, 246, 0.12); color: #3b82f6; border: 1px solid rgba(59, 130, 246, 0.3); padding: 4px 14px; border-radius: 9999px; font-size: 0.85em; font-weight: 600;">Illustrious-XL Base</span>
<span style="background: rgba(16, 185, 129, 0.12); color: #10b981; border: 1px solid rgba(16, 185, 129, 0.3); padding: 4px 14px; border-radius: 9999px; font-size: 0.85em; font-weight: 600;">ComfyUI Ready</span>
</div>
<div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/6a8370b3938db6517c63e020/IzQ2HkYV28hS1xNBPd4r6.png" alt="Voidmix Showcase" style="border-radius: 14px; box-shadow: 0 10px 30px -5px rgba(0,0,0,0.3); max-width: 100%; height: auto;" />
</div>
<p style="margin-top: 14px; font-size: 1.05em; max-width: 720px; line-height: 1.6;">
An SDXL diffusion model merged and tuned from <b>Illustrious-XL</b>, crafted specifically for atmospheric, volumetric, and high-fidelity stylized anime illustration.
</p>
</div>
<div style="background: rgba(107, 114, 128, 0.08); border-left: 3px solid #9333ea; border-radius: 6px; padding: 10px 16px; margin: 20px 0; font-size: 0.85em; color: #6b7280; line-height: 1.5;">
Showcase renders utilize the bundled face and body detailers. No external color grading was applied beyond a subtle vignette.
</div>
<div align="center">
<div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/6a8370b3938db6517c63e020/ZVdxnvtfRDG0ncZOb6Z24.png" alt="Voidmix Showcase" style="border-radius: 14px; box-shadow: 0 10px 30px -5px rgba(0,0,0,0.3); max-width: 100%; height: 400px;" />
</div>
</div>
---
### βš™οΈ Recommended Generation Parameters
| Parameter | Recommended Setting | Notes |
| :--- | :--- | :--- |
| **Sampler** | `euler_ancestral` | Works great with `normal` scheduler |
| **Steps** | `25 – 35` | 28 is the sweet spot |
| **CFG Scale** | `5.0 – 7.0` | Keep lower to avoid burnout |
| **Clip Skip** | `2` | Set last layer to `-2` |
| **VAE** | `sdxl.vae.safetensors` | Included in repository `/vae` |
| **CLIP** | Dual Clip (`illustrious_clip_l` & `illustrious_clip_g`) | Load via `Load CLIP (Dual)` node |
---
<div align="center">
<div>
<img src="https://cdn-uploads.huggingface.co/production/uploads/6a8370b3938db6517c63e020/cMtzg3dNKIx12AzMaJwSE.png" alt="Voidmix Showcase" style="border-radius: 14px; box-shadow: 0 10px 30px -5px rgba(0,0,0,0.3); max-width: 100%; height: 300px;" />
</div>
</div>
### πŸš€ Quick Start (ComfyUI)
<div style="border: 1px solid rgba(147, 51, 234, 0.25); background: rgba(147, 51, 234, 0.03); border-radius: 12px; padding: 18px; margin: 16px 0;">
1. **Place Model Assets:**
- Put models from `/diffusion_models` &rarr; `ComfyUI/models/diffusion_models/`
- Put encoders from `/text_encoders` &rarr; `ComfyUI/models/text_encoders/`
- Put `/vae` files &rarr; `ComfyUI/models/vae/`
2. **Load Official Workflow:** Download `workflow.json` from the root of this repo and drag it directly into ComfyUI.
3. **Generate:** Add your positive prompt and click **Run**.
</div>