debug 9

app.py

@@ -1,95 +1,67 @@
-# import gradio as gr
-# from diffusers import DiffusionPipeline
-# import torch
-# from diffusers import DDPMScheduler, UNet2DModel
-# from PIL import Image
-# import numpy as np
-
-
-# def erzeuge(prompt):
-#     return pipeline(prompt).images  # [0]
+import gradio as gr
+from diffusers import DiffusionPipeline
+import torch
+from diffusers import DDPMScheduler, UNet2DModel
+from PIL import Image
+import numpy as np
 
 
-# def erzeuge_komplex(prompt):
-#     scheduler = DDPMScheduler.from_pretrained("google/ddpm-cat-256")
-#     model = UNet2DModel.from_pretrained("google/ddpm-cat-256").to("cuda")
-#     scheduler.set_timesteps(50)
+def erzeuge(prompt):
+    return pipeline(prompt).images  # [0]
 
-#     sample_size = model.config.sample_size
-#     noise = torch.randn((1, 3, sample_size, sample_size)).to("cuda")
-#     input = noise
 
-#     for t in scheduler.timesteps:
-#         with torch.no_grad():
-#             noisy_residual = model(input, t).sample
-#             prev_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
-#             input = prev_noisy_sample
+def erzeuge_komplex(prompt):
+    scheduler = DDPMScheduler.from_pretrained("google/ddpm-cat-256")
+    model = UNet2DModel.from_pretrained("google/ddpm-cat-256").to("cuda")
+    scheduler.set_timesteps(50)
 
-#     image = (input / 2 + 0.5).clamp(0, 1)
-#     image = image.cpu().permute(0, 2, 3, 1).numpy()[0]
-#     image = Image.fromarray((image * 255).round().astype("uint8"))
-#     return image
+    sample_size = model.config.sample_size
+    noise = torch.randn((1, 3, sample_size, sample_size)).to("cuda")
+    input = noise
 
+    for t in scheduler.timesteps:
+        with torch.no_grad():
+            noisy_residual = model(input, t).sample
+            prev_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
+            input = prev_noisy_sample
 
-# # pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2")
-# # pipeline = DiffusionPipeline.from_pretrained("google/ddpm-cat-256")
-# pipeline = DiffusionPipeline.from_pretrained("google/ddpm-celebahq-256")
+    image = (input / 2 + 0.5).clamp(0, 1)
+    image = image.cpu().permute(0, 2, 3, 1).numpy()[0]
+    image = Image.fromarray((image * 255).round().astype("uint8"))
+    return image
 
-# # pipeline.to("cuda")
 
+# pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2")
+# pipeline = DiffusionPipeline.from_pretrained("google/ddpm-cat-256")
+pipeline = DiffusionPipeline.from_pretrained("google/ddpm-celebahq-256")
 
-# with gr.Blocks() as demo:
-#     with gr.Column(variant="panel"):
-#         with gr.Row(variant="compact"):
-#             text = gr.Textbox(
-#                 label="Deine Beschreibung:",
-#                 show_label=False,
-#                 max_lines=1,
-#                 placeholder="Bildbeschreibung",
-#             ).scale(
-#                 container=False,
-#             )
-#             btn = gr.Button("erzeuge Bild").style(full_width=False, min_width=100)
+# pipeline.to("cuda")
 
-#         gallery = gr.Gallery(
-#             label="Erzeugtes Bild", show_label=False, elem_id="gallery"
-#         ).style(columns=[2], rows=[2], object_fit="contain", height="auto")
 
-#     btn.click(erzeuge, inputs=[text], outputs=[gallery])
-#     text.submit(erzeuge, inputs=[text], outputs=[gallery])
+with gr.Blocks() as demo:
+    with gr.Column(variant="panel"):
+        with gr.Row(variant="compact"):
+            text = gr.Textbox(
+                label="Deine Beschreibung:",
+                show_label=False,
+                max_lines=1,
+                placeholder="Bildbeschreibung",
+            )
+            btn = gr.Button("erzeuge Bild").style(full_width=False, min_width=100)
 
-# if __name__ == "__main__":
-#     demo.launch()
+        gallery = gr.Gallery(
+            label="Erzeugtes Bild", show_label=False, elem_id="gallery"
+        ).style(columns=[2], rows=[2], object_fit="contain", height="auto")
 
+    btn.click(erzeuge, inputs=[text], outputs=[gallery])
+    text.submit(erzeuge, inputs=[text], outputs=[gallery])
 
+if __name__ == "__main__":
+    demo.launch()
 
 
 
 
 
-from diffusers import DiffusionPipeline
-from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline
-import torch
-import gradio as gr
-import random
 
-pipeline = DiffusionPipeline.from_pretrained("google/ddpm-celebahq-256")
-# pipeline.to("cuda")
 
-def predict(steps, seed):
-    generator = torch.manual_seed(seed)
-    for i in range(1,steps):
-        yield pipeline(generator=generator, num_inference_steps=i).images[0]
-
-random_seed = random.randint(0, 2147483647)
-gr.Interface(
-    predict,
-    inputs=[
-        gr.inputs.Slider(1, 100, label='Inference Steps', default=5, step=1),
-        gr.inputs.Slider(0, 2147483647, label='Seed', default=random_seed, step=1),
-    ],
-    outputs=gr.Image(shape=[128,128], type="pil", elem_id="output_image"),
-    css="#output_image{width: 256px}",
-    title="Unconditional butterflies",
-    description="图片生成器",
-).queue().launch()