Upload README.MD

README.MD

@@ -0,0 +1,196 @@
+---
+language:
+  - en
+pipeline_tag: text-to-image
+library_name: diffusers
+tags:
+  - text-to-image
+  - stable-diffusion
+  - safetensors
+  - anime
+  - merge
+license: openrail++
+base_model:
+  - neta-art/Neta-Lumina
+  - hanzogak/comradeshipLUv2
+---
+
+<style>
+  .container {
+    display: flex;
+    gap: 2rem;
+    align-items: flex-start;
+  }
+  .image-wrapper,
+  .details {
+    flex: 1 1 50%;
+  }
+  .image-wrapper {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+  }
+  .model-image {
+    width: 100%;
+    max-width: 500px;
+    min-width: 300px;
+    border-radius: 8px;
+    box-shadow: 0 8px 20px rgba(0, 0, 0, 0.3);
+  }
+  .details h1 {
+    margin-top: 0;
+    font-size: 2rem;
+    color: #fff;
+  }
+  .details .description {
+    margin: 0.5rem 0 1.5rem;
+    line-height: 1.5;
+    color: #ccc;
+  }
+  .badge-list {
+    list-style: none;
+    padding: 0;
+    margin: 0;
+    display: flex;
+    flex-wrap: wrap;
+    row-gap: 0.25rem;
+    column-gap: 0.5rem;
+  }
+  .badge-list li {
+    margin: 0;
+  }
+  .badge-btn {
+    display: inline-flex;
+    align-items: center;
+    height: 28px;
+    padding: 0 10px;
+    font-size: 14px;
+    font-weight: 500;
+    color: #fff;
+    text-decoration: none;
+    border-radius: 4px;
+    white-space: nowrap;
+    transition: opacity 0.2s, transform 0.1s;
+  }
+  .badge-btn .btn-icon {
+    width: 16px;
+    height: 16px;
+    margin-right: 6px;
+  }
+  .badge-btn:hover {
+    opacity: 0.85;
+    transform: translateY(-1px);
+  }
+  .badge-btn.hf {
+    background-color: #ff66008d;
+  }
+  @media (max-width: 700px) {
+    .container {
+      flex-direction: column;
+      align-items: center;
+    }
+    .image-wrapper,
+    .details {
+      flex: unset;
+      width: 100%;
+    }
+    .model-image {
+      width: 90%;
+      max-width: 500px;
+      min-width: auto;
+      margin-bottom: 1rem;
+    }
+  }
+</style>
+
+<div class="container">
+  <div class="image-wrapper">
+    <!-- Replace with your own example image -->
+    <img
+      src="https://huggingface.co/rityak/LumiNetaMix/resolve/main/cover.png"
+      alt="Neta Lumina Custom Merge Example"
+      class="model-image"
+    />
+  </div>
+  <div class="details">
+    <h1>Neta Lumina Custom Merge v1.0</h1>
+    <p class="description">
+      <strong>Neta Lumina Custom Merge</strong> builds on the open-source 
+      <a href="https://huggingface.co/neta-art/Neta-Lumina" target="_blank">Neta‑Lumina</a>  
+      checkpoint using a custom <code>karcher_mean</code> merge. It preserves the original anime‑style aesthetic 
+      while delivering enhanced NSFW support and slight gains in generation quality—especially with simple 
+      and Danbooru tags.
+    </p>
+    <ul class="badge-list">
+      <li>
+        <a
+          href="https://huggingface.co/your-username/your-repo/resolve/main/model.safetensors?download=true"
+          target="_blank"
+          class="badge-btn hf"
+        >
+          <img
+            src="https://huggingface.co/front/assets/huggingface_logo-noborder.svg"
+            alt="Hugging Face"
+            class="btn-icon"
+          />
+          Download Model
+        </a>
+      </li>
+      <li>
+        <a
+          href="https://neta.art/blog/neta_lumina_prompt_book/"
+          target="_blank"
+          class="badge-btn"
+        >
+          Prompt Book
+        </a>
+      </li>
+      <li>
+        <a
+          href="https://huggingface.co/api/resolve-cache/models/neta-art/Neta-Lumina/d1d432a44a84f160d9e8791f704e0d3895ae6ae1/lumina_workflow.json"
+          target="_blank"
+          class="badge-btn hf"
+        >
+          ComfyUI Workflow
+        </a>
+      </li>
+    </ul>
+  </div>
+</div>
+
+- **Original Model**  
+  Building on the open-source [Neta‑Lumina](https://huggingface.co/neta-art/Neta-Lumina) checkpoint.
+- **Prompt Book**  
+  Full prompt guidelines and tag list: [neta_lumina_prompt_book](https://neta.art/blog/neta_lumina_prompt_book/)
+- **ComfyUI Workflow**  
+  Pre-made workflow for ComfyUI:  
+  [Download JSON](https://huggingface.co/api/resolve-cache/models/neta-art/Neta-Lumina/d1d432a44a84f160d9e8791f704e0d3895ae6ae1/lumina_workflow.json)
+
+## Model Details
+
+- **Model type**: diffusion-based text-to-image
+- **Base checkpoint**: neta-art/Neta-Lumina
+- **Merge method**: `karcher_mean` custom merge
+
+## Key Improvements
+
+- **Enhanced NSFW support**
+- **Slight quality gains** with both simple and Danbooru prompt tags
+- **Maintains original anime aesthetic** and multilingual tag comprehension
+
+- **Recommended Settings**
+
+  - Sampler: `res_multistep`
+  - Scheduler: `linear_quadratic`
+  - Steps: 30
+  - CFG Scale: 4.0 – 5.5
+  - Resolution: ≥ 1024×1024
+
+## Downloads
+
+- **All‑in‑One (AIO) Version**  
+  [Download the AIO model (UNET + Text Encoder + VAE)](https://huggingface.co/rityak/LumiNetaMix/resolve/main/LumiNetaMix.safetensors?download=true)
+
+- **Separate Components**
+  - **UNET checkpoint**: [Download UNET](https://huggingface.co/rityak/LumiNetaMix/resolve/main/LumiNetaMix_unet.safetensors?download=true)
+  - **Text Encoder**: [Download Text Encoder](https://huggingface.co/rityak/LumiNetaMix/resolve/main/LumiNetaMix_gemma2_2b.safetensors?download=true)