Update app_quant_latent.py

app_quant_latent.py

@@ -593,9 +593,9 @@ async def async_upload_latents(latent_dict, filename, LOGS):
         LOGS.append(f"⚠️ Failed to upload all preview latents: {e}")
 
 
-        
+# this code genetae all frame for latest GPU expseinve bt decide fails sp use this later         
 @spaces.GPU
-def generate_image(prompt, height, width, steps, seed, guidance_scale=0.0):
+def generate_image_all_latents(prompt, height, width, steps, seed, guidance_scale=0.0):
     LOGS = []
     device = "cpu"  # FORCE CPU
     generator = torch.Generator(device).manual_seed(int(seed))
@@ -688,8 +688,94 @@ def generate_image(prompt, height, width, steps, seed, guidance_scale=0.0):
         yield placeholder, latent_gallery, LOGS
 
 # this is astable vesopn tha can gen final and a noise to latent
+
+
 @spaces.GPU
-def generate_image0(prompt, height, width, steps, seed, guidance_scale=0.0):
+def generate_image(prompt, height, width, steps, seed, guidance_scale=0.0):
+    LOGS = []
+    device = "cuda"
+    generator = torch.Generator(device).manual_seed(int(seed))
+
+    placeholder = Image.new("RGB", (width, height), color=(255, 255, 255))
+    latent_gallery = []
+    final_gallery = []
+
+    # --- Generate latent previews in a loop ---
+    try:
+        latents = safe_get_latents(pipe, height, width, generator, device, LOGS)
+
+        # always keep latents float32 until decode
+        latents = latents.float()
+
+        num_previews = min(10, steps)
+        preview_steps = torch.linspace(0, 1, num_previews)
+
+        for i, alpha in enumerate(preview_steps):
+
+            try:
+                with torch.no_grad():
+
+                    # simulate progression
+                    preview_latent = latents * alpha + torch.randn_like(latents) * (1 - alpha)
+
+                    # 🛠 FIX: match VAE dtype
+                    vae_dtype = pipe.vae.dtype
+                    preview_latent = preview_latent.to(vae_dtype)
+
+                    # decode
+                    latent_img_tensor = pipe.vae.decode(preview_latent).sample
+                    latent_img_tensor = (latent_img_tensor / 2 + 0.5).clamp(0, 1)
+                    latent_img_tensor = latent_img_tensor.cpu().permute(0,2,3,1)[0]
+                    latent_img = Image.fromarray((latent_img_tensor.numpy() * 255).astype("uint8"))
+
+            except Exception as e:
+                LOGS.append(f"⚠️ Latent preview decode failed: {e}")
+                latent_img = placeholder
+
+            latent_gallery.append(latent_img)
+            yield None, latent_gallery, LOGS
+
+        # Upload latents
+        latent_dict = {"latents": latents.cpu(), "prompt": prompt, "seed": seed}
+        try:
+            hf_url = upload_latents_to_hf(latent_dict, filename=f"latents_{seed}.pt")
+            LOGS.append(f"🔹 Latents uploaded: {hf_url}")
+        except Exception as e:
+            LOGS.append(f"⚠️ Failed to upload latents: {e}")
+
+    except Exception as e:
+        LOGS.append(f"⚠️ Latent generation failed: {e}")
+        latent_gallery.append(placeholder)
+        yield None, latent_gallery, LOGS
+
+    # --- Final image: untouched standard pipeline ---
+    try:
+        output = pipe(
+            prompt=prompt,
+            height=height,
+            width=width,
+            num_inference_steps=steps,
+            guidance_scale=guidance_scale,
+            generator=generator,
+        )
+        final_img = output.images[0]
+        final_gallery.append(final_img)
+        latent_gallery.append(final_img)  # fallback preview if needed
+        LOGS.append("✅ Standard pipeline succeeded.")
+        yield final_img, latent_gallery, LOGS
+
+    except Exception as e2:
+        LOGS.append(f"❌ Standard pipeline failed: {e2}")
+        final_gallery.append(placeholder)
+        latent_gallery.append(placeholder)
+        yield placeholder, latent_gallery, LOGS
+
+
+
+
+# this is astable vesopn tha can gen final and a noise to latent
+@spaces.GPU
+def generate_image_safe(prompt, height, width, steps, seed, guidance_scale=0.0):
     LOGS = []
     device = "cuda"
     generator = torch.Generator(device).manual_seed(int(seed))
@@ -768,9 +854,6 @@ def generate_image0(prompt, height, width, steps, seed, guidance_scale=0.0):
 
 
 
-
-
-
 with gr.Blocks(title="Z-Image-Turbo") as demo:
     gr.Markdown("# 🎨 DO NOT RUN THIS ")
     with gr.Tabs():