Upload 6 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/0052/oe.jpg filter=lfs diff=lfs merge=lfs -text
+examples/0052/ue.jpg filter=lfs diff=lfs merge=lfs -text
+examples/0072/oe.jpg filter=lfs diff=lfs merge=lfs -text
+examples/0072/ue.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,154 +1,231 @@
+# -*- coding: utf-8 -*-
+import os
+import sys
 import gradio as gr
 import numpy as np
 import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
+import spaces #[uncomment to use ZeroGPU]
+# from diffusers import DiffusionPipeline
 import torch
+from torchvision.transforms import ToTensor, ToPILImage
+import logging
+logging.getLogger("huggingface_hub").setLevel(logging.CRITICAL)
+from huggingface_hub import hf_hub_download, snapshot_download
+
+model_name = "iimmortall/UltraFusion"
+auth_token = os.getenv("HF_AUTH_TOKEN")
+# print(auth_token)
+# greet_file = hf_hub_download(repo_id=model_name, filename="main.py", use_auth_token=auth_token) 
+# sys.path.append(os.path.split(greet_file)[0])  
+model_folder = snapshot_download(repo_id=model_name, token=auth_token)
+# sys.path.append(model_folder)
+sys.path.insert(0, model_folder)
+print(sys.path)
+# exit()
+
+from ultrafusion_utils import load_model, run_ultrafusion
+
+to_tensor = ToTensor()
+to_pil = ToPILImage()
+ultrafusion_pipe, flow_model = load_model()
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
 if torch.cuda.is_available():
     torch_dtype = torch.float16
 else:
     torch_dtype = torch.float32
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
+@spaces.GPU(duration=10) #[uncomment to use ZeroGPU]
 def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
+    under_expo_img,
+    over_expo_img,
+    # progress=gr.Progress(track_tqdm=True),
 ):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
+    # if randomize_seed:
+    #     seed = random.randint(0, MAX_SEED)
+    # generator = torch.Generator().manual_seed(seed)
 
-    generator = torch.Generator().manual_seed(seed)
+    # image = pipe(
+    #     prompt=prompt,
+    #     negative_prompt=negative_prompt,
+    #     guidance_scale=guidance_scale,
+    #     num_inference_steps=num_inference_steps,
+    #     width=width,
+    #     height=height,
+    #     generator=generator,
+    # ).images[0]
 
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
+    print(under_expo_img.size)
+    print("reciving image")
 
-    return image, seed
+    under_expo_img = under_expo_img.resize([1500, 1000])
+    over_expo_img = over_expo_img.resize([1500, 1000])
 
+    ue = to_tensor(under_expo_img).unsqueeze(dim=0).to("cuda")
+    oe = to_tensor(over_expo_img).unsqueeze(dim=0).to("cuda")
 
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
+    out = run_ultrafusion(ue, oe, 'test', flow_model=flow_model, pipe=ultrafusion_pipe, consistent_start=None)
+
+    out = out.clamp(0, 1).squeeze()
+    out_pil = to_pil(out)
+
+    return out_pil
 
+
+examples= [
+    [os.path.join("examples", img_name, "ue.jpg"), 
+     os.path.join("examples", img_name, "oe.jpg")] for img_name in sorted(os.listdir("examples"))
+]
+IMG_W = 320
+IMG_H = 240
 css = """
 #col-container {
     margin: 0 auto;
     max-width: 640px;
 }
 """
+# max-heigh: 1500px;
+
+_HEADER_ = '''
+<h2><b>Official 🤗 UltraHDR Demo</b></h2><h2><a href='' target='_blank'><b>UltraHDR: xxx</b></a></h2>
+'''
+
+_CITE_ = r"""
+📝 **Citation**
+
+If you find our work useful for your research or applications, please cite using this bibtex:
+```bibtex
+@article{xxx,
+  title={xxx},
+  author={xxx},
+  journal={arXiv preprint arXiv:xx.xx},
+  year={2024}
+}
+```
 
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
+📋 **License**
 
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
+CC BY-NC 4.0. LICENSE.
 
-            run_button = gr.Button("Run", scale=0, variant="primary")
+📧 **Contact**
 
-        result = gr.Image(label="Result", show_label=False)
+If you have any questions, feel free to open a discussion or contact us at <b>xxx@gmail.com</b>.
+"""
 
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(" # UltraHDR")
+        with gr.Row():
+            under_expo_img = gr.Image(label="UnderExposureImage", show_label=True,
+                image_mode="RGB",
+                sources=["upload", ],
+                width=IMG_W,
+                height=IMG_H,
+                type="pil"
             )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
+            over_expo_img = gr.Image(label="OverExposureImage", show_label=True, 
+                image_mode="RGB",
+                sources=["upload", ],
+                width=IMG_W,
+                height=IMG_H,
+                type="pil"
             )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+        with gr.Row():
+            run_button = gr.Button("Run", variant="primary") # scale=0, 
+        
+        result = gr.Image(label="Result", show_label=True, 
+                          type='pil', 
+                          image_mode='RGB', 
+                          format="png",
+                          width=IMG_W*2,
+                          height=IMG_H*2,
+                        )
+
+        # with gr.Row():
+        # prompt = gr.Text(
+        #     label="Prompt",
+        #     show_label=False,
+        #     max_lines=1,
+        #     placeholder="Enter your prompt",
+        #     container=False,
+        # )
+        # negative_prompt = gr.Text(
+        #     label="Negative prompt",
+        #     max_lines=1,
+        #     placeholder="Enter a negative prompt",
+        #     visible=False,
+        # )
+        # with gr.Accordion("Advanced Settings", open=False):
+        #     negative_prompt = gr.Text(
+        #         label="Negative prompt",
+        #         max_lines=1,
+        #         placeholder="Enter a negative prompt",
+        #         visible=False,
+        #     )
+
+        #     seed = gr.Slider(
+        #         label="Seed",
+        #         minimum=0,
+        #         maximum=MAX_SEED,
+        #         step=1,
+        #         value=0,
+        #     )
+
+        #     randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+
+        #     with gr.Row():
+        #         width = gr.Slider(
+        #             label="Width",
+        #             minimum=256,
+        #             maximum=MAX_IMAGE_SIZE,
+        #             step=32,
+        #             value=1024,  # Replace with defaults that work for your model
+        #         )
+
+        #         height = gr.Slider(
+        #             label="Height",
+        #             minimum=256,
+        #             maximum=MAX_IMAGE_SIZE,
+        #             step=32,
+        #             value=1024,  # Replace with defaults that work for your model
+        #         )
+
+        #     with gr.Row():
+        #         guidance_scale = gr.Slider(
+        #             label="Guidance scale",
+        #             minimum=0.0,
+        #             maximum=10.0,
+        #             step=0.1,
+        #             value=0.0,  # Replace with defaults that work for your model
+        #         )
+
+        #         num_inference_steps = gr.Slider(
+        #             label="Number of inference steps",
+        #             minimum=1,
+        #             maximum=50,
+        #             step=1,
+        #             value=2,  # Replace with defaults that work for your model
+        #         )
+       
+        gr.Examples(
+            examples=examples, 
+            inputs=[under_expo_img, over_expo_img], 
+            label="Examples",
+            # examples_per_page=10,
+            cache_examples=False,
+            # fn=infer,
+            )
+        # gr.Markdown(_CITE_)
+    run_button.click(fn=infer,
+                     inputs=[under_expo_img, over_expo_img],
+                     outputs=[result,],
+                    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.queue(max_size=10)
+    demo.launch(share=True)
+    # demo.launch(server_name="0.0.0.0", debug=True, show_api=True, show_error=True, share=False)

requirements.txt

@@ -1,15 +1,15 @@
-accelerate
-diffusers
-invisible_watermark
-transformers
-xformers
-torch==2.4.1
-torchvision==0.19.1
-omegaconf
-numpy
-pillow
-einops
-scipy
-numpy
-ftfy
+accelerate
+diffusers
+invisible_watermark
+transformers
+xformers
+torch==2.4.1
+torchvision==0.19.1
+omegaconf
+numpy
+pillow
+einops
+scipy
+numpy
+ftfy
 pytorch_lightning==2.4