import gradio as gr import numpy as np import random # import spaces #[uncomment to use ZeroGPU] from diffusers import DiffusionPipeline import torch 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] def infer( prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True), ): if randomize_seed: seed = random.randint(0, MAX_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] return image, seed examples = [ "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", "An astronaut riding a green horse", "A delicious ceviche cheesecake slice", ] css = """ #col-container { margin: 0 auto; max-width: 640px; } """ with gr.Blocks(css=css) as demo: with gr.Column(elem_id="col-container"): gr.Markdown(" # Text-to-Image Gradio Template") with gr.Row(): prompt = gr.Text( label="Prompt", show_label=False, max_lines=1, placeholder="Enter your prompt", container=False, ) run_button = gr.Button("Run", scale=0, variant="primary") result = gr.Image(label="Result", show_label=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=[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], ) if __name__ == "__main__": demo.launch(share=True) # import gradio as gr # import shutil # import os # import subprocess # import sys # # Run the .bat file before launching the app # """try: # import PromptTrack # except ImportError: # print("PromptTrack not found. Installing...") # subprocess.run([sys.executable, "-m", "pip", "install", # "--index-url", "https://test.pypi.org/simple/", # "--extra-index-url", "https://pypi.org/simple/", # "PromptTrack"], check=True) # subprocess.run([sys.executable, "-m", "pip", "install", # "--no-deps", "bytetracker"], check=True) # import PromptTrack # Retry import after installation # from PromptTrack import PromptTracker # tracker = PromptTracker()""" # def process_video(video_path, prompt): # detection_threshold=0.3 # track_thresh=0.4 # match_thresh=1 # max_time_lost=float("inf") # nbr_frames_fixing=800 # output_video = video_path.split('mp4')[0]+"_with_id.mp4" # Placeholder for processed video # output_file = video_path.split('mp4')[0]+"_mot_.json" # Tracking result # output_file_2 = video_path.split('mp4')[0]+"_object_detection.json" # detection results # video_file = video_path # """tracker.detect_objects(video_file, prompt=prompt, nms_threshold=0.8, detection_threshold=detection_threshold, detector="OWL-VITV2") # tracker.process_mot(video_file, fixed_parc=True, track_thresh=track_thresh, match_thresh=match_thresh, frame_rate=25, max_time_lost=max_time_lost, nbr_frames_fixing=nbr_frames_fixing) # tracker.read_video_with_mot(video_file, fps=25) # """ # output_video = "output.mp4" # Placeholder for processed video # output_file = "output.txt" # Placeholder for generated file # # Copy the input video to simulate processing # shutil.copy(video_path.name, output_video) # # Create an output text file with the prompt content # with open(output_file, "w") as f: # f.write(f"User Prompt: {prompt}\n") # return output_video, output_file # # Define Gradio interface # iface = gr.Interface( # fn=process_video, # inputs=[gr.File(label="Upload Video"), gr.Textbox(placeholder="Enter your prompt")], # outputs=[gr.Video(), gr.File(label="Generated File")], # title="Video Processing App", # description="Upload a video and enter a prompt. The app will return the processed video and a generated file." # ) # # Launch the app # '''if __name__ == "__main__": # iface.launch() # ''' # import gradio as gr # import shutil # import os # def process_video(video, prompt): # output_video = "output.mp4" # Placeholder for processed video # output_file = "output.txt" # Placeholder for generated file # # Copy the input video to simulate processing # shutil.copy(video.name, output_video) # # Create an output text file with the prompt content # with open(output_file, "w") as f: # f.write(f"User Prompt: {prompt}\n") # return output_video, output_file # # Define Gradio interface # iface = gr.Interface( # fn=process_video, # inputs=[gr.File(label="Upload Video"), gr.Textbox(placeholder="Enter your prompt")], # outputs=[gr.Video(), gr.File(label="Generated File")], # title="Video Processing App", # description="Upload a video and enter a prompt. The app will return the processed video and a generated file." # ) # # Launch the app # if __name__ == "__main__": # iface.launch(share=True)