Link, prompt, time & stat

app.py

@@ -70,7 +70,7 @@ def reset():
         None,
         None,
         "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, aliasing, bokeh, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
+        "painting, oil painting, illustration, drawing, art, sketch, anime, cartoon, CG Style, 3D render, unreal engine, blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
         1,
         1024,
         1,
@@ -377,25 +377,25 @@ def restore_on_gpu(
 
     torch.cuda.set_device(SUPIR_device)
 
-    input_image = upscale_image(input_image, upscale, unit_resolution=32, min_size=min_size)
-    LQ = np.array(input_image) / 255.0
-    LQ = np.power(LQ, gamma_correction)
-    LQ *= 255.0
-    LQ = LQ.round().clip(0, 255).astype(np.uint8)
-    LQ = LQ / 255 * 2 - 1
-    LQ = torch.tensor(LQ, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(SUPIR_device)[:, :3, :, :]
-    captions = ['']
-
     with torch.no_grad():
+        input_image = upscale_image(input_image, upscale, unit_resolution=32, min_size=min_size)
+        LQ = np.array(input_image) / 255.0
+        LQ = np.power(LQ, gamma_correction)
+        LQ *= 255.0
+        LQ = LQ.round().clip(0, 255).astype(np.uint8)
+        LQ = LQ / 255 * 2 - 1
+        LQ = torch.tensor(LQ, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(SUPIR_device)[:, :3, :, :]
+        captions = ['']
+
         samples = model.batchify_sample(LQ, captions, num_steps=edm_steps, restoration_scale=s_stage1, s_churn=s_churn,
                                     s_noise=s_noise, cfg_scale=s_cfg, control_scale=s_stage2, seed=seed,
                                     num_samples=num_samples, p_p=a_prompt, n_p=n_prompt, color_fix_type=color_fix_type,
                                     use_linear_CFG=linear_CFG, use_linear_control_scale=linear_s_stage2,
                                     cfg_scale_start=spt_linear_CFG, control_scale_start=spt_linear_s_stage2)
 
-    x_samples = (einops.rearrange(samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().round().clip(
-        0, 255).astype(np.uint8)
-    results = [x_samples[i] for i in range(num_samples)]
+        x_samples = (einops.rearrange(samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().round().clip(
+            0, 255).astype(np.uint8)
+        results = [x_samples[i] for i in range(num_samples)]
     torch.cuda.empty_cache()
 
     # All the results have the same size
@@ -426,7 +426,7 @@ def restore_on_gpu(
         print("edm_steps: " + str(edm_steps))
         print("num_samples: " + str(num_samples))
         print("downscale: " + str(downscale))
-        print("Estimated minutes: " + f'{(((result_width * result_height**(1/1.5)) * input_width * input_height * (edm_steps**(1/2)) * (num_samples**(1/2.5)))**(1/2.5)) / 30000:,}')
+        print("Estimated minutes: " + f'{(((result_width * result_height**(1/1.5)) * input_width * input_height * (edm_steps**(1/2)) * (num_samples**(1/2.5)))**(1/2.5)) / 25000:,}')
     except Exception as e:
         print('Exception of Estimation')
 
@@ -492,7 +492,7 @@ title_html = """
     SUPIR is for beauty and illustration only.
     Most of the processes only last few minutes.
     The process will be aborted if it lasts more than 10 min.
-    If you want to upscale AI-generated images, be noticed that <i>Stable Diffusion 3 Medium</i> spaces can directly generate 1536x1536 images.
+    If you want to upscale AI-generated images, be noticed that <i>PixArt Sigma</i> space can directly generate 5984x5984 images.
     Due to Gradio issues, the generated image is slightly less satured than the original.
     Please leave a <a href="https://huggingface.co/spaces/Fabrice-TIERCELIN/SUPIR/discussions/new">message in discussion</a> if you encounter issues.
     You can also use <a href="https://huggingface.co/spaces/gokaygokay/AuraSR">AuraSR</a> to upscale x4.
@@ -532,7 +532,7 @@ with gr.Blocks() as interface:
         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], ["x9", 9], ["x10", 10]], label="Upscale factor", info="Resolution x1 to x10", 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 (discouraged)", 8], ["9 min (discouraged)", 9], ["10 min (discouraged)", 10]], label="GPU allocation time", info="lower=May abort run, higher=Quota penalty for next runs", value=6, 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 (discouraged)", 8], ["9 min (discouraged)", 9], ["10 min (discouraged)", 10]], label="GPU allocation time", info="lower=May abort run, higher=Quota penalty for next runs", value=7, interactive=True)
         output_format = gr.Radio([["As input", "input"], ["*.png", "png"], ["*.webp", "webp"], ["*.jpeg", "jpeg"], ["*.gif", "gif"], ["*.bmp", "bmp"]], label="Image format for result", info="File extention", value="input", interactive=True)
 
     with gr.Accordion("Pre-denoising (optional)", open=False):
@@ -552,7 +552,7 @@ with gr.Blocks() as interface:
         n_prompt = gr.Textbox(label="Negative image description",
                               info="Disambiguate by listing what the image does NOT represent",
                               value='painting, oil painting, illustration, drawing, art, sketch, anime, '
-                                    'cartoon, CG Style, 3D render, unreal engine, blurring, aliasing, bokeh, ugly, dirty, messy, '
+                                    'cartoon, CG Style, 3D render, unreal engine, blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, '
                                     'worst quality, low quality, frames, watermark, signature, jpeg artifacts, '
                                     'deformed, lowres, over-smooth',
                               lines=3)
@@ -611,7 +611,7 @@ with gr.Blocks() as interface:
                     None,
                     "Group of people, walking, happy, in the street, photorealistic, 8k, extremely detailled",
                     "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, aliasing, bokeh, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
+                    "painting, oil painting, illustration, drawing, art, sketch, anime, cartoon, CG Style, 3D render, unreal engine, blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
                     2,
                     1024,
                     1,
@@ -642,7 +642,7 @@ with gr.Blocks() as interface:
                     None,
                     "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, aliasing, bokeh, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
+                    "painting, oil painting, illustration, drawing, art, sketch, anime, cartoon, CG Style, 3D render, unreal engine, blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
                     1,
                     1024,
                     1,
@@ -673,7 +673,7 @@ with gr.Blocks() as interface:
                     None,
                     "A red apple",
                     "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, aliasing, bokeh, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
+                    "painting, oil painting, illustration, drawing, art, sketch, anime, cartoon, CG Style, 3D render, unreal engine, blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
                     1,
                     1024,
                     1,
@@ -704,7 +704,7 @@ with gr.Blocks() as interface:
                     None,
                     "A red marble",
                     "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, aliasing, bokeh, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
+                    "painting, oil painting, illustration, drawing, art, sketch, anime, cartoon, CG Style, 3D render, unreal engine, blurring, aliasing, unsharp, weird textures, ugly, dirty, messy, worst quality, low quality, frames, watermark, signature, jpeg artifacts, deformed, lowres, over-smooth",
                     1,
                     1024,
                     1,