Update app.py

app.py

@@ -1,48 +1,69 @@
 import gradio as gr
-from PIL import Image
 import os
 import random
+from PIL import Image
 import spaces
-
+import torch
+from transformers import MllamaForConditionalGeneration, AutoProcessor
 from OmniGen import OmniGenPipeline
 
-pipe = OmniGenPipeline.from_pretrained(
-    "Shitao/OmniGen-v1"
-)
+pipe = OmniGenPipeline.from_pretrained("Shitao/OmniGen-v1")
+model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+model = MllamaForConditionalGeneration.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto",)
+processor = AutoProcessor.from_pretrained(model_id)
+
+@spaces.GPU()
+def predict_clothing(images):
+    messages = [{"role": "user", "content":
+                 [
+                     {"type": "image"},
+                     {"type": "text", "text": "Define this clothing in 1-3 words. Your response should be only the definition."}
+                 ]}
+               ]
+    input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
+
+    output_texts = []
+    for image in images:
+        inputs = processor(image, input_text, add_special_tokens=False, return_tensors="pt").to(model.device)
+        with torch.no_grad():
+            output = model.generate(**inputs, max_new_tokens=30)
+        output_texts.append(str(processor.decode(output[0])))
+
+    return output_texts
+    
 
 @spaces.GPU(duration=180)
-def generate_image(text, img1, img2, img3, height, width, guidance_scale, img_guidance_scale, inference_steps, seed, separate_cfg_infer, offload_model,
-            use_input_image_size_as_output, max_input_image_size, randomize_seed):
+def generate_image(img1, img2, img3, height, width, img_guidance_scale, inference_steps, seed, separate_cfg_infer, offload_model,
+                   use_input_image_size_as_output, max_input_image_size, randomize_seed, guidance_scale=3.5):
+    
     input_images = [img1, img2, img3]
     # Delete None
     input_images = [img for img in input_images if img is not None]
     if len(input_images) == 0:
         input_images = None
+
+    wears = predict_clothing(input_images[1:])
+    if len(wears)==1:
+        dress = wears[0]
+        text = """A male wearing a {dress}. The male is in <img><|image_1|></img>. The {dress} is in <img><|image_2|></img>."""
+    elif len(wears)==2:
+        topwear, bottomwear = wears[0], wears[1]
+        text = """A male wearing a {topwear} and a {bottomwear}. The male is in <img><|image_1|></img>.
+                    The {topwear} is in <img><|image_2|></img>. The {bottomwear} is in <img><|image_3|></img>."""
+    else:
+        input_images = None
+        
     
     if randomize_seed:
         seed = random.randint(0, 10000000)
 
-    output = pipe(
-        prompt=text,
-        input_images=input_images,
-        height=height,
-        width=width,
-        guidance_scale=guidance_scale,
-        img_guidance_scale=img_guidance_scale,
-        num_inference_steps=inference_steps,
-        separate_cfg_infer=separate_cfg_infer, 
-        use_kv_cache=True,
-        offload_kv_cache=True,
-        offload_model=offload_model,
-        use_input_image_size_as_output=use_input_image_size_as_output,
-        seed=seed,
-        max_input_image_size=max_input_image_size,
-    )
+    output = pipe(prompt=text, input_images=input_images, height=height, width=width, guidance_scale=guidance_scale,
+                  img_guidance_scale=img_guidance_scale, num_inference_steps=inference_steps, separate_cfg_infer=separate_cfg_infer, 
+                  use_kv_cache=True, offload_kv_cache=True, offload_model=offload_model, 
+                  use_input_image_size_as_output=use_input_image_size_as_output, seed=seed, max_input_image_size=max_input_image_size,)
     img = output[0]
     return img
 
-
-
 def get_example():
     case = [
         [
@@ -245,164 +266,109 @@ def get_example():
     return case
 
 def run_for_examples(text, img1, img2, img3, height, width, guidance_scale, img_guidance_scale, seed, max_input_image_size, randomize_seed, use_input_image_size_as_output):    
-    # 在函数内部设置默认值
+    # Check the internal configuration of the function
     inference_steps = 50
     separate_cfg_infer = True
     offload_model = False
     
-    return generate_image(
-        text, img1, img2, img3, height, width, guidance_scale, img_guidance_scale, 
-        inference_steps, seed, separate_cfg_infer, offload_model,
-        use_input_image_size_as_output, max_input_image_size, randomize_seed
-    )
+    return generate_image(text, img1, img2, img3, height, width, guidance_scale, img_guidance_scale, inference_steps, seed,
+                          separate_cfg_infer, offload_model, use_input_image_size_as_output, max_input_image_size, randomize_seed)
 
 description = """
-OmniGen is a unified image generation model that you can use to perform various tasks, including but not limited to text-to-image generation, subject-driven generation, Identity-Preserving Generation, and image-conditioned generation.
-For multi-modal to image generation, you should pass a string as `prompt`, and a list of image paths as `input_images`. The placeholder in the prompt should be in the format of `<img><|image_*|></img>` (for the first image, the placeholder is <img><|image_1|></img>. for the second image, the the placeholder is <img><|image_2|></img>).
-For example, use an image of a woman to generate a new image:
-prompt = "A woman holds a bouquet of flowers and faces the camera. Thw woman is \<img\>\<|image_1|\>\</img\>."
+This is a Virtual Try-On Platform.
+Usage:
+- First upload your own image as the first image, also tagged 'Person'
+- Then upload you 'Top-wear' and 'Bottom-wear' images
+- If its a single dress, and/or you don't have a Topwear and Bottomwear as separate images upload that single image under 'Topwear'
+
 Tips:
 - For image editing task and controlnet task, we recommend setting the height and width of output image as the same as input image. For example, if you want to edit a 512x512 image, you should set the height and width of output image as 512x512. You also can set the `use_input_image_size_as_output` to automatically set the height and width of output image as the same as input image.
 - For out-of-memory or time cost, you can set `offload_model=True` or refer to [./docs/inference.md#requiremented-resources](https://github.com/VectorSpaceLab/OmniGen/blob/main/docs/inference.md#requiremented-resources) to select a appropriate setting.
 - If inference time is too long when inputting multiple images, please try to reduce the `max_input_image_size`. For more details please refer to [./docs/inference.md#requiremented-resources](https://github.com/VectorSpaceLab/OmniGen/blob/main/docs/inference.md#requiremented-resources).
-- Oversaturated: If the image appears oversaturated, please reduce the `guidance_scale`.
-- Low-quality: More detailed prompts will lead to better results. 
-- Animate Style: If the generated images are in animate style, you can try to add `photo` to the prompt`.
-- Edit generated image. If you generate an image by omnigen and then want to edit it, you cannot use the same seed to edit this image. For example, use seed=0 to generate image, and should use seed=1 to edit this image.
-- For image editing tasks, we recommend placing the image before the editing instruction. For example, use `<img><|image_1|></img> remove suit`, rather than `remove suit <img><|image_1|></img>`. 
-
 
 **HF Spaces often encounter errors due to quota limitations, so recommend to run it locally.**
 """
 
-article = """
----
-**Citation** 
-<br> 
-If you find this repository useful, please consider giving a star ⭐ and a citation
-```
-@article{xiao2024omnigen,
-  title={Omnigen: Unified image generation},
-  author={Xiao, Shitao and Wang, Yueze and Zhou, Junjie and Yuan, Huaying and Xing, Xingrun and Yan, Ruiran and Wang, Shuting and Huang, Tiejun and Liu, Zheng},
-  journal={arXiv preprint arXiv:2409.11340},
-  year={2024}
-}
-```
-**Contact**
-<br>
-If you have any questions, please feel free to open an issue or directly reach us out via email.
+Credits = """**Credits** 
+Made using [OmniGen](https://huggingface.co/Shitao/OmniGen-v1): Unified Image Generation [paper](https://arxiv.org/abs/2409.11340) [code](https://github.com/VectorSpaceLab/OmniGen)
 """
 
 
 # Gradio 
 with gr.Blocks() as demo:
-    gr.Markdown("# OmniGen: Unified Image Generation [paper](https://arxiv.org/abs/2409.11340) [code](https://github.com/VectorSpaceLab/OmniGen)")
+    gr.Markdown("Virtual Try-On")
     gr.Markdown(description)
     with gr.Row():
-        with gr.Column():
-            # text prompt
-            prompt_input = gr.Textbox(
-                label="Enter your prompt, use <img><|image_i|></img> to represent i-th input image", placeholder="Type your prompt here..."
-            )
-
-            with gr.Row(equal_height=True):
-                # input images
-                image_input_1 = gr.Image(label="<img><|image_1|></img>", type="filepath")
-                image_input_2 = gr.Image(label="<img><|image_2|></img>", type="filepath")
-                image_input_3 = gr.Image(label="<img><|image_3|></img>", type="filepath")
+        with gr.Row(equal_height=True):
+            # input images
+            image_input_1 = gr.Image(label="Person", type="filepath")
+            image_input_2 = gr.Image(label="Top-wear", type="filepath")
+            image_input_3 = gr.Image(label="Bottom-wear", type="filepath")
 
-            # slider
-            height_input = gr.Slider(
-                label="Height", minimum=128, maximum=2048, value=1024, step=16
-            )
-            width_input = gr.Slider(
-                label="Width", minimum=128, maximum=2048, value=1024, step=16
-            )
+        # slider
+        height_input = gr.Slider(
+            label="Height", minimum=128, maximum=2048, value=1024, step=16
+        )
+        width_input = gr.Slider(
+            label="Width", minimum=128, maximum=2048, value=1024, step=16
+        )
 
-            guidance_scale_input = gr.Slider(
-                label="Guidance Scale", minimum=1.0, maximum=5.0, value=2.5, step=0.1
-            )
+        guidance_scale_input = gr.Slider(
+            label="Guidance Scale", minimum=1.0, maximum=5.0, value=2.5, step=0.1
+        )
 
-            img_guidance_scale_input = gr.Slider(
-                label="img_guidance_scale", minimum=1.0, maximum=2.0, value=1.6, step=0.1
-            )
+        img_guidance_scale_input = gr.Slider(
+            label="img_guidance_scale", minimum=1.0, maximum=2.0, value=1.6, step=0.1
+        )
 
-            num_inference_steps = gr.Slider(
-                label="Inference Steps", minimum=1, maximum=100, value=50, step=1
-            )
+        num_inference_steps = gr.Slider(
+            label="Inference Steps", minimum=1, maximum=100, value=50, step=1
+        )
 
-            seed_input = gr.Slider(
-                label="Seed", minimum=0, maximum=2147483647, value=42, step=1
-            )
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        seed_input = gr.Slider(
+            label="Seed", minimum=0, maximum=2147483647, value=42, step=1
+        )
+        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
 
-            max_input_image_size = gr.Slider(
-                label="max_input_image_size", minimum=128, maximum=2048, value=1024, step=16
-            )
+        max_input_image_size = gr.Slider(
+            label="max_input_image_size", minimum=128, maximum=2048, value=1024, step=16
+        )
 
-            separate_cfg_infer = gr.Checkbox(
-                label="separate_cfg_infer", info="Whether to use separate inference process for different guidance. This will reduce the memory cost.", value=True,
-            )
-            offload_model = gr.Checkbox(
-                label="offload_model", info="Offload model to CPU, which will significantly reduce the memory cost but slow down the generation speed. You can cancel separate_cfg_infer and set offload_model=True. If both separate_cfg_infer and offload_model are True, further reduce the memory, but slowest generation", value=False,
-            )
-            use_input_image_size_as_output = gr.Checkbox(
-                label="use_input_image_size_as_output", info="Automatically adjust the output image size to be same as input image size. For editing and controlnet task, it can make sure the output image has the same size as input image leading to better performance", value=False,
-            )
+        separate_cfg_infer = gr.Checkbox(
+            label="separate_cfg_infer", info="Whether to use separate inference process for different guidance. This will reduce the memory cost.", value=True,
+        )
+        offload_model = gr.Checkbox(
+            label="offload_model", info="Offload model to CPU, which will significantly reduce the memory cost but slow down the generation speed. You can cancel separate_cfg_infer and set offload_model=True. If both separate_cfg_infer and offload_model are True, further reduce the memory, but slowest generation", value=False,
+        )
+        use_input_image_size_as_output = gr.Checkbox(
+            label="use_input_image_size_as_output", info="Automatically adjust the output image size to be same as input image size. For editing and controlnet task, it can make sure the output image has the same size as input image leading to better performance", value=False,
+        )
 
-            # generate
-            generate_button = gr.Button("Generate Image")
+        # generate
+        generate_button = gr.Button("Generate Image")
             
-
-        with gr.Column():
-            # output image
-            output_image = gr.Image(label="Output Image")
+    with gr.Row():
+        # output image
+        output_image = gr.Image(label="Output Image")
 
     # click
     generate_button.click(
         generate_image,
-        inputs=[
-            prompt_input,
-            image_input_1,
-            image_input_2,
-            image_input_3,
-            height_input,
-            width_input,
-            guidance_scale_input,
-            img_guidance_scale_input,
-            num_inference_steps,
-            seed_input,
-            separate_cfg_infer,
-            offload_model,
-            use_input_image_size_as_output,
-            max_input_image_size,
-            randomize_seed,
-        ],
+        inputs=[image_input_1, image_input_2, image_input_3, height_input, width_input, img_guidance_scale_input, num_inference_steps,
+                seed_input, separate_cfg_infer, offload_model, use_input_image_size_as_output, max_input_image_size, randomize_seed,
+                guidance_scale_input,],
         outputs=output_image,
     )
 
     gr.Examples(
         examples=get_example(),
         fn=run_for_examples,
-        inputs=[
-            prompt_input,
-            image_input_1,
-            image_input_2,
-            image_input_3,
-            height_input,
-            width_input,
-            guidance_scale_input,
-            img_guidance_scale_input,
-            seed_input,
-            max_input_image_size,
-            randomize_seed,
-            use_input_image_size_as_output,
-        ],
+        inputs=[image_input_1, image_input_2, image_input_3, height_input, width_input, img_guidance_scale_input, seed_input,
+                max_input_image_size, randomize_seed, use_input_image_size_as_output,guidance_scale_input],
         outputs=output_image,
     )
 
-    gr.Markdown(article)
+    gr.Markdown(Credits)
 
 # launch
-demo.launch()
-
+demo.launch()