Fix VLM: use Llama-4-Scout via nscale (confirmed working with images), Kimi-K2.6 and Qwen3.5-9B via together as fallbacks

app.py

@@ -65,17 +65,14 @@ Apply the edit and return ONLY the complete updated JSON (no markdown, no explan
   }}
 }}"""
 
-# Actual Vision-Language Models with correct providers
+# Verified working VLMs (tested 2026-04-25)
+# Llama-4-Scout: confirmed image support, answers in content field
+# Kimi-K2.6: image support, answers in reasoning field
+# Qwen3.5-9B: image support unclear, answers in reasoning field
 VISION_MODELS = [
-    ("Qwen/Qwen2.5-VL-72B-Instruct", "together", "Qwen2.5-VL 72B"),
-    ("google/gemma-4-31B-it", "novita", "Gemma 4 31B"),
-    ("moonshotai/Kimi-K2.5", "fireworks-ai", "Kimi K2.5"),
-]
-# Text-only models (for chat edit without images)
-TEXT_MODELS = [
-    ("Qwen/Qwen2.5-VL-72B-Instruct", "together", "Qwen2.5-VL 72B"),
-    ("google/gemma-4-31B-it", "novita", "Gemma 4 31B"),
-    ("moonshotai/Kimi-K2.5", "fireworks-ai", "Kimi K2.5"),
+    ("meta-llama/Llama-4-Scout-17B-16E-Instruct", "nscale", "Llama-4-Scout 17B"),
+    ("moonshotai/Kimi-K2.6", "together", "Kimi K2.6"),
+    ("Qwen/Qwen3.5-9B", "together", "Qwen 3.5 9B"),
 ]
 
 def _extract_response_text(message):
@@ -293,7 +290,7 @@ CSS = """
 with gr.Blocks(title="Garment Pattern Studio") as demo:
     gr.HTML("""<div class="main-header"><h1>🧵 Garment Pattern Studio</h1>
         <p style="font-size:1.1em;color:#555;">Analyze garments, edit with chat, preview in 3D, refine with AI agent</p></div>
-    <div class="info-box"><b>Powered by:</b> Qwen2.5-VL 72B · Gemma 4 31B · Kimi K2.5 via
+    <div class="info-box"><b>Powered by:</b> Llama-4-Scout · Kimi K2.6 · Qwen 3.5 via
         <a href="https://huggingface.co/docs/inference-providers">HF Inference Providers</a>
         &nbsp;|&nbsp; <b>3D view built from actual 2D pattern pieces</b></div>""")
 
@@ -367,17 +364,11 @@ with gr.Blocks(title="Garment Pattern Studio") as demo:
         chat_clear.click(clear_chat, outputs=[chatbot, chat_pattern_2d, chat_3d, chat_summary, chat_json])
 
     with gr.Tab("🔄 Agentic Refinement"):
-        gr.Markdown("""### Iterative Refinement Loop
-Upload a garment image. The AI agent will:
-1. **Analyze** → extract initial pattern parameters via VLM
-2. **Generate** → create 2D pattern + 3D garment from pattern pieces
-3. **Project** → render 3D to 2D front view
-4. **Compare** → SSIM + Edge-SSIM similarity metrics
-5. **VLM Assess** → visual comparison, identify differences, suggest adjustments
-6. **Refine** → apply damped parameter updates, keep-best tracking
-7. **Repeat** until convergence or max iterations
-
-*Requires HF_TOKEN for VLM-powered refinement.*""")
+        gr.Markdown("""### ⚠️ Work In Progress — Iterative Refinement Loop
+Upload a garment image. The AI agent will iteratively refine pattern parameters.
+See [README](https://huggingface.co/spaces/vikashmakeit/garment-to-pattern) for full design docs.
+
+**Status:** Core components (projection, similarity, convergence loop) work. VLM feedback integration needs further testing.""")
         with gr.Row():
             with gr.Column(scale=1):
                 refine_image = gr.Image(type="pil", label="Upload Garment Image", height=300)