, type="filepath"

app.py

@@ -86,7 +86,7 @@ def stage1_process(
         gr.Warning('Set this space to GPU config to make it work.')
         return None, None
     torch.cuda.set_device(SUPIR_device)
-    LQ = HWC3(input_image)
+    LQ = HWC3(Image.open(input_image))
     LQ = fix_resize(LQ, 512)
     # stage1
     LQ = np.array(LQ) / 255 * 2 - 1
@@ -187,19 +187,19 @@ def stage2_process(
         a_prompt = prompt + a_prompt
     print("Final prompt: " + str(a_prompt))
 
-    noisy_image = noisy_image if denoise_image is None else denoise_image
+    denoise_image = Image.open(noisy_image if denoise_image is None else denoise_image)
 
     if rotation == 90:
-        noisy_image = np.array(list(zip(*noisy_image[::-1])))
+        denoise_image = np.array(list(zip(*denoise_image[::-1])))
     elif rotation == 180:
-        noisy_image = np.array(list(zip(*noisy_image[::-1])))
-        noisy_image = np.array(list(zip(*noisy_image[::-1])))
+        denoise_image = np.array(list(zip(*denoise_image[::-1])))
+        denoise_image = np.array(list(zip(*denoise_image[::-1])))
     elif rotation == -90:
-        noisy_image = np.array(list(zip(*noisy_image))[::-1])
+        denoise_image = np.array(list(zip(*denoise_image))[::-1])
 
     if 1 < downscale:
-        input_height, input_width, input_channel = noisy_image.shape
-        noisy_image = np.array(Image.fromarray(noisy_image).resize((input_width // downscale, input_height // downscale), Image.LANCZOS))
+        input_height, input_width, input_channel = denoise_image.shape
+        denoise_image = denoise_image.resize((input_width // downscale, input_height // downscale), Image.LANCZOS)
 
     # Allocation
     if allocation == 1:
@@ -284,8 +284,8 @@ def restore_in_10min(*args, **kwargs):
     return restore(*args, **kwargs)
 
 def restore(
+    noisy_image,
     input_image,
-    denoise_image,
     prompt,
     a_prompt,
     n_prompt,
@@ -467,10 +467,10 @@ with gr.Blocks() as interface:
     """)
     gr.HTML(title_html)
 
-    input_image = gr.Image(label="Input (*.png, *.webp, *.jpeg, *.gif, *.bmp)", show_label=True, type="numpy", height=600, elem_id="image-input")
+    input_image = gr.Image(label="Input (*.png, *.webp, *.jpeg, *.gif, *.bmp)", show_label=True, type="filepath", height=600, elem_id="image-input")
     rotation = gr.Radio([["No rotation", 0], ["⤵ Rotate +90°", 90], ["↩ Return 180°", 180], ["⤴ Rotate -90°", -90]], label="Orientation correction", info="Will apply the following rotation before restoring the image; the AI needs a good orientation to understand the content", value=0, interactive=True, visible=False)
     with gr.Group():
-        prompt = gr.Textbox(label="Image description", info="Help the AI understand what the image represents; describe as much as possible, especially the details we can't see on the original image; I advise you to write in English because other languages may not be handled", value="", placeholder="A 33 years old man, walking, in the street, Santiago, morning, Summer, photorealistic", lines=3)
+        prompt = gr.Textbox(label="Image description", info="Help the AI understand what the image represents; describe as much as possible, especially the details we can't see on the original image; you can write in any language", value="", placeholder="A 33 years old man, walking, in the street, Santiago, morning, Summer, photorealistic", lines=3)
         prompt_hint = gr.HTML("You can use a <a href='"'https://huggingface.co/spaces/MaziyarPanahi/llava-llama-3-8b'"'>LlaVa space</a> to auto-generate the description of your image.")
         upscale = gr.Radio([["x1", 1], ["x2", 2], ["x3", 3], ["x4", 4], ["x5", 5], ["x6", 6], ["x7", 7], ["x8", 8]], label="Upscale factor", info="Resolution x1 to x8", value=2, interactive=True)
         allocation = gr.Radio([["1 min", 1], ["2 min", 2], ["3 min", 3], ["4 min", 4], ["5 min", 5], ["6 min", 6], ["7 min", 7], ["8 min", 8]], label="GPU allocation time", info="lower=May abort run, higher=Quota penalty for next runs", value=6, interactive=True)
@@ -479,7 +479,7 @@ with gr.Blocks() as interface:
     with gr.Accordion("Pre-denoising (optional)", open=False):
         gamma_correction = gr.Slider(label="Gamma Correction", info = "lower=lighter, higher=darker", minimum=0.1, maximum=2.0, value=1.0, step=0.1)
         denoise_button = gr.Button(value="Pre-denoise")
-        denoise_image = gr.Image(label="Denoised image", show_label=True, type="numpy", sources=[], height=600, elem_id="image-s1")
+        denoise_image = gr.Image(label="Denoised image", show_label=True, type="filepath", sources=[], height=600, elem_id="image-s1")
         denoise_information = gr.HTML(value="If present, the denoised image will be used for the restoration instead of the input image.", visible=False)
 
     with gr.Accordion("Advanced options", open=False):
@@ -618,7 +618,7 @@ with gr.Blocks() as interface:
                     "./Examples/Example2.jpeg",
                     0,
                     None,
-                    "The head of a tabby cat, in a house, photorealistic, 8k, extremely detailled",
+                    "La cabeza de un gato atigrado, en una casa, fotorrealista, 8k, extremadamente detallada",
                     "Cinematic, High Contrast, highly detailed, taken using a Canon EOS R camera, hyper detailed photo - realistic maximum detail, 32k, Color Grading, ultra HD, extreme meticulous detailing, skin pore detailing, hyper sharpness, perfect without deformations.",
                     "painting, oil painting, illustration, drawing, art, sketch, anime, cartoon, CG Style, 3D render, unreal engine, blurring, bokeh, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
                     1,