feat: add three new SDXL/SD1.5 image generation models

Add the following models to models_huggingface.yaml:
- John6666/diving-illustrious-real-asian-v50-sdxl: SDXL fine-tune for photorealistic Asian subjects
- playgroundai/playground-v2.5-1024px-aesthetic: High-aesthetic 1024px SDXL-based model
- Lykon/dreamshaper-8: Versatile SD1.5 fine-tune with multi-style support

All models marked as non-essential and will download .safetensors files.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

models_huggingface.yaml

@@ -105,6 +105,45 @@ model_categories:
         - source: "sd3.5_large.safetensors"
           dest: "sd3.5_large.safetensors"
 
+    - repo_id: John6666/diving-illustrious-real-asian-v50-sdxl
+      description: Diving Illustrious Real Asian v5.0 - Photorealistic Asian subjects
+      size_gb: 7
+      essential: false
+      category: image
+      type: checkpoints
+      format: fp16
+      vram_gb: 12
+      notes: SDXL fine-tune specializing in photorealistic Asian subjects with illustrious quality
+      files:
+        - source: "*.safetensors"
+          dest: "diving-illustrious-real-asian-v50-sdxl.safetensors"
+
+    - repo_id: playgroundai/playground-v2.5-1024px-aesthetic
+      description: Playground v2.5 - 1024px aesthetic images
+      size_gb: 7
+      essential: false
+      category: image
+      type: checkpoints
+      format: fp16
+      vram_gb: 12
+      notes: Highly aesthetic 1024x1024 outputs, outperforms SDXL and DALL-E 3 in user studies
+      files:
+        - source: "*.safetensors"
+          dest: "playground-v2.5-1024px-aesthetic.safetensors"
+
+    - repo_id: Lykon/dreamshaper-8
+      description: DreamShaper 8 - Multi-style versatile model
+      size_gb: 4
+      essential: false
+      category: image
+      type: checkpoints
+      format: fp16
+      vram_gb: 8
+      notes: Versatile SD1.5 fine-tune balancing photorealistic and anime styles with strong LoRA support
+      files:
+        - source: "*.safetensors"
+          dest: "dreamshaper-8.safetensors"
+
   # ==========================================================================
   # VIDEO GENERATION MODELS
   # ==========================================================================