Update app.py

app.py

@@ -1,50 +1,64 @@
+"""
+Gradio demo per Shap-E (text-to-3D) – Hugging Face Spaces
+Autore: tu
+"""
+
+import os
 import gradio as gr
 import torch
-import trimesh
-
-# Assicurati di aver installato i pacchetti:
-# pip install get3d gradio trimesh
-
-from get3d.models import get_model
-from get3d.configs import MODEL_CONFIGS
-
-# Configurazione: scegli un modello pretrained (es: 'chair', 'car', 'table')
-MODEL_NAME = 'chair'
-config = MODEL_CONFIGS[MODEL_NAME]
+from shap_e.diffusion.sample import sample_latents
+from shap_e.diffusion.gaussian_diffusion import diffusion_from_config
+from shap_e.models.download import load_model, load_config
+from shap_e.util.notebooks import decode_latent_mesh
 
+# ---------- caricamento modelli ----------
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-# Carica il modello GET3D pretrained
-model = get_model(config).to(device)
-model.eval()
-
-
-def generate_mesh(prompt: str) -> str:
-    """
-    Genera una mesh 3D casuale basata sul prompt (demo non testuale) e la salva come .obj
-    """
-    # GET3D non supporta direttamente text-to-3D; qui usiamo un vettore latente casuale
-    z = torch.randn(1, config.z_dim, device=device)
-    with torch.no_grad():
-        verts, faces = model.generate_mesh(z)
-
-    # Costruisci l'oggetto Trimesh e salvalo
-    mesh = trimesh.Trimesh(vertices=verts[0].cpu().numpy(), faces=faces[0].cpu().numpy())
-    output_path = f"/mnt/data/mesh_{torch.randint(0,1e6,(1,)).item()}.obj"
-    mesh.export(output_path)
-    return output_path
+xm = load_model('transmitter', device=device)
+model = load_model('text300M', device=device)
+diffusion = diffusion_from_config(load_config('diffusion'))
 
+# ---------- logica ----------
+def generate(prompt: str,
+             guidance: float = 15.0,
+             steps: int = 64):
+    """Genera la mesh e restituisce il file .ply scaricabile."""
+    latents = sample_latents(
+        batch_size=1,
+        model=model,
+        diffusion=diffusion,
+        guidance_scale=guidance,
+        model_kwargs=dict(texts=[prompt]),
+        progress=True,
+        clip_denoised=True,
+        use_fp16=True,
+        use_karras=True,
+        karras_steps=steps,
+        sigma_min=1e-3,
+        sigma_max=160,
+        s_churn=0,
+    )
 
-def respond(message, history):
-    # history è una lista di tuple (user, bot)
-    mesh_file = generate_mesh(message)
-    bot_msg = f"Mesh generata! Scarica qui: {{}}".format(mesh_file)
-    history.append((message, bot_msg))
-    return history
+    t = decode_latent_mesh(xm, latents[0]).tri_mesh()
+    out_path = "output.ply"
+    with open(out_path, "wb") as f:
+        t.write_ply(f)
+    return out_path
 
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot(label="Chatbot GET3D")
-    txt = gr.Textbox(placeholder="Inserisci un prompt per la mesh...")
-    txt.submit(respond, [txt, chatbot], chatbot)
+# ---------- interfaccia Gradio ----------
+iface = gr.Interface(
+    fn=generate,
+    inputs=[
+        gr.Textbox(label="Prompt"),
+        gr.Slider(1, 30, value=15, label="Guidance scale"),
+        gr.Slider(32, 128, value=64, step=16, label="Karras steps")
+    ],
+    outputs=gr.File(label="Scarica mesh .ply"),
+    title="Shap-E Text-to-3D",
+    description="Genera una mesh 3D da una descrizione testuale con Shap-E.",
+    examples=[["a high–quality red sports car"],
+              ["a cute low-poly cat"]],
+    cache_examples=False   # vogliamo sempre generare
+)
 
 if __name__ == "__main__":
-    demo.launch()  # Imposta share=True se vuoi ottenere un link pubblico
+    iface.launch()