Update app.py

app.py

@@ -103,6 +103,7 @@ def generate_caption(image):
         prompt = task_prompt
 
         inputs = florence_processor(text=prompt, images=image, return_tensors="pt").to(device)
+        inputs["pixel_values"] = inputs["pixel_values"].to(torch.float16)  # Match model dtype
         
         generated_ids = florence_model.generate(
             input_ids=inputs["input_ids"],
@@ -190,6 +191,9 @@ def tiled_flux_img2img(pipe, prompt, image, strength, steps, guidance, generator
                 generator=generator,
             ).images[0]
 
+            # Resize back to exact tile size if pipeline adjusted it
+            gen_tile = gen_tile.resize((tile_w, tile_h), resample=Image.LANCZOS)
+
             # Paste with blending if overlap
             if overlap > 0:
                 paste_box = (x, y, x + tile_w, y + tile_h)
@@ -197,12 +201,14 @@ def tiled_flux_img2img(pipe, prompt, image, strength, steps, guidance, generator
                     # Simple linear blend on overlaps
                     mask = Image.new('L', (tile_w, tile_h), 255)
                     if x > 0:
-                        for i in range(overlap):
+                        blend_width = min(overlap, tile_w)
+                        for i in range(blend_width):
                             for j in range(tile_h):
                                 mask.putpixel((i, j), int(255 * (i / overlap)))
                     if y > 0:
+                        blend_height = min(overlap, tile_h)
                         for i in range(tile_w):
-                            for j in range(overlap):
+                            for j in range(blend_height):
                                 mask.putpixel((i, j), int(255 * (j / overlap)))
                     output.paste(gen_tile, paste_box, mask)
                 else: