Update app.py

app.py

@@ -1,10 +1,11 @@
 """
-THis is the main file for the gradio web demo. It uses the CogVideoX-5B model to generate videos gradio web demo.
+THis is the main file for the gradio web demo. It uses the CogVideoX1.5-5B model to generate videos gradio web demo.
 set environment variable OPENAI_API_KEY to use the OpenAI API to enhance the prompt.
 
 Usage:
     OpenAI_API_KEY=your_openai_api_key OPENAI_BASE_URL=https://api.openai.com/v1 python inference/gradio_web_demo.py
 """
+import spaces
 
 import math
 import os
@@ -17,8 +18,11 @@ import tempfile
 import imageio_ffmpeg
 import gradio as gr
 import torch
+from torchao.quantization import quantize_, int8_weight_only
+from transformers import T5EncoderModel
 from PIL import Image
 from diffusers import (
+    AutoencoderKLCogVideoX,
     CogVideoXPipeline,
     CogVideoXDPMScheduler,
     CogVideoXVideoToVideoPipeline,
@@ -27,26 +31,49 @@ from diffusers import (
 )
 from diffusers.utils import load_video, load_image
 from datetime import datetime, timedelta
-
 from diffusers.image_processor import VaeImageProcessor
-from openai import OpenAI
+#from openai import OpenAI
 import moviepy.editor as mp
 import utils
-from rife_model import load_rife_model, rife_inference_with_latents
-from huggingface_hub import hf_hub_download, snapshot_download
+#from rife_model import load_rife_model, rife_inference_with_latents
+#from huggingface_hub import hf_hub_download, snapshot_download
 import gc
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-hf_hub_download(repo_id="ai-forever/Real-ESRGAN", filename="RealESRGAN_x4.pth", local_dir="model_real_esran")
-snapshot_download(repo_id="AlexWortega/RIFE", local_dir="model_rife")
-
-pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16).to("cpu")
+#hf_hub_download(repo_id="ai-forever/Real-ESRGAN", filename="RealESRGAN_x4.pth", local_dir="model_real_esran")
+#snapshot_download(repo_id="AlexWortega/RIFE", local_dir="model_rife")
+quantization = int8_weight_only
+
+transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX1.5-5B", subfolder="transformer", torch_dtype=torch.bfloat16)
+text_encoder = T5EncoderModel.from_pretrained("THUDM/CogVideoX1.5-5B", subfolder="text_encoder", torch_dtype=torch.bfloat16)
+vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX1.5-5B", subfolder="vae", torch_dtype=torch.bfloat16)
+quantize_(transformer, quantization())
+quantize_(text_encoder, quantization())
+# quantize_(vae, quantization())
+
+pipe = CogVideoXPipeline.from_pretrained(
+    "THUDM/CogVideoX1.5-5B",
+    text_encoder=text_encoder,
+    transformer=transformer,
+    vae=vae,
+    torch_dtype=torch.bfloat16
+    ).to("cpu")
 pipe.scheduler = CogVideoXDPMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")
 
+pipe.enable_model_cpu_offload()
+pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()
+
 i2v_transformer = CogVideoXTransformer3DModel.from_pretrained(
-    "THUDM/CogVideoX-5b-I2V", subfolder="transformer", torch_dtype=torch.bfloat16
+    "THUDM/CogVideoX1.5-5B-I2V", subfolder="transformer", torch_dtype=torch.bfloat16
 )
+i2v_text_encoder = T5EncoderModel.from_pretrained("THUDM/CogVideoX1.5-5B-I2V", subfolder="text_encoder", torch_dtype=torch.bfloat16)
+i2v_vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX1.5-5B-I2V", subfolder="vae", torch_dtype=torch.bfloat16)
+
+quantize_(i2v_transformer, quantization())
+quantize_(i2v_text_encoder, quantization())
+# quantize_(i2v_vae, quantization())
 
 # pipe.transformer.to(memory_format=torch.channels_last)
 # pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)
@@ -56,8 +83,8 @@ i2v_transformer = CogVideoXTransformer3DModel.from_pretrained(
 os.makedirs("./output", exist_ok=True)
 os.makedirs("./gradio_tmp", exist_ok=True)
 
-upscale_model = utils.load_sd_upscale("model_real_esran/RealESRGAN_x4.pth", device)
-frame_interpolation_model = load_rife_model("model_rife")
+#upscale_model = utils.load_sd_upscale("model_real_esran/RealESRGAN_x4.pth", device)
+#frame_interpolation_model = load_rife_model("model_rife")
 
 sys_prompt = """You are part of a team of bots that creates videos. You work with an assistant bot that will draw anything you say in square brackets.
 
@@ -147,54 +174,54 @@ def center_crop_resize(input_video_path, target_width=720, target_height=480):
     return temp_video_path
 
 
-def convert_prompt(prompt: str, retry_times: int = 3) -> str:
-    if not os.environ.get("OPENAI_API_KEY"):
-        return prompt
-    client = OpenAI()
-    text = prompt.strip()
-
-    for i in range(retry_times):
-        response = client.chat.completions.create(
-            messages=[
-                {"role": "system", "content": sys_prompt},
-                {
-                    "role": "user",
-                    "content": 'Create an imaginative video descriptive caption or modify an earlier caption for the user input : "a girl is on the beach"',
-                },
-                {
-                    "role": "assistant",
-                    "content": "A radiant woman stands on a deserted beach, arms outstretched, wearing a beige trench coat, white blouse, light blue jeans, and chic boots, against a backdrop of soft sky and sea. Moments later, she is seen mid-twirl, arms exuberant, with the lighting suggesting dawn or dusk. Then, she runs along the beach, her attire complemented by an off-white scarf and black ankle boots, the tranquil sea behind her. Finally, she holds a paper airplane, her pose reflecting joy and freedom, with the ocean's gentle waves and the sky's soft pastel hues enhancing the serene ambiance.",
-                },
-                {
-                    "role": "user",
-                    "content": 'Create an imaginative video descriptive caption or modify an earlier caption for the user input : "A man jogging on a football field"',
-                },
-                {
-                    "role": "assistant",
-                    "content": "A determined man in athletic attire, including a blue long-sleeve shirt, black shorts, and blue socks, jogs around a snow-covered soccer field, showcasing his solitary exercise in a quiet, overcast setting. His long dreadlocks, focused expression, and the serene winter backdrop highlight his dedication to fitness. As he moves, his attire, consisting of a blue sports sweatshirt, black athletic pants, gloves, and sneakers, grips the snowy ground. He is seen running past a chain-link fence enclosing the playground area, with a basketball hoop and children's slide, suggesting a moment of solitary exercise amidst the empty field.",
-                },
-                {
-                    "role": "user",
-                    "content": 'Create an imaginative video descriptive caption or modify an earlier caption for the user input : " A woman is dancing, HD footage, close-up"',
-                },
-                {
-                    "role": "assistant",
-                    "content": "A young woman with her hair in an updo and wearing a teal hoodie stands against a light backdrop, initially looking over her shoulder with a contemplative expression. She then confidently makes a subtle dance move, suggesting rhythm and movement. Next, she appears poised and focused, looking directly at the camera. Her expression shifts to one of introspection as she gazes downward slightly. Finally, she dances with confidence, her left hand over her heart, symbolizing a poignant moment, all while dressed in the same teal hoodie against a plain, light-colored background.",
-                },
-                {
-                    "role": "user",
-                    "content": f'Create an imaginative video descriptive caption or modify an earlier caption in ENGLISH for the user input: "{text}"',
-                },
-            ],
-            model="glm-4-plus",
-            temperature=0.01,
-            top_p=0.7,
-            stream=False,
-            max_tokens=200,
-        )
-        if response.choices:
-            return response.choices[0].message.content
-    return prompt
+# def convert_prompt(prompt: str, retry_times: int = 3) -> str:
+#     if not os.environ.get("OPENAI_API_KEY"):
+#         return prompt
+#     client = OpenAI()
+#     text = prompt.strip()
+
+#     for i in range(retry_times):
+#         response = client.chat.completions.create(
+#             messages=[
+#                 {"role": "system", "content": sys_prompt},
+#                 {
+#                     "role": "user",
+#                     "content": 'Create an imaginative video descriptive caption or modify an earlier caption for the user input : "a girl is on the beach"',
+#                 },
+#                 {
+#                     "role": "assistant",
+#                     "content": "A radiant woman stands on a deserted beach, arms outstretched, wearing a beige trench coat, white blouse, light blue jeans, and chic boots, against a backdrop of soft sky and sea. Moments later, she is seen mid-twirl, arms exuberant, with the lighting suggesting dawn or dusk. Then, she runs along the beach, her attire complemented by an off-white scarf and black ankle boots, the tranquil sea behind her. Finally, she holds a paper airplane, her pose reflecting joy and freedom, with the ocean's gentle waves and the sky's soft pastel hues enhancing the serene ambiance.",
+#                 },
+#                 {
+#                     "role": "user",
+#                     "content": 'Create an imaginative video descriptive caption or modify an earlier caption for the user input : "A man jogging on a football field"',
+#                 },
+#                 {
+#                     "role": "assistant",
+#                     "content": "A determined man in athletic attire, including a blue long-sleeve shirt, black shorts, and blue socks, jogs around a snow-covered soccer field, showcasing his solitary exercise in a quiet, overcast setting. His long dreadlocks, focused expression, and the serene winter backdrop highlight his dedication to fitness. As he moves, his attire, consisting of a blue sports sweatshirt, black athletic pants, gloves, and sneakers, grips the snowy ground. He is seen running past a chain-link fence enclosing the playground area, with a basketball hoop and children's slide, suggesting a moment of solitary exercise amidst the empty field.",
+#                 },
+#                 {
+#                     "role": "user",
+#                     "content": 'Create an imaginative video descriptive caption or modify an earlier caption for the user input : " A woman is dancing, HD footage, close-up"',
+#                 },
+#                 {
+#                     "role": "assistant",
+#                     "content": "A young woman with her hair in an updo and wearing a teal hoodie stands against a light backdrop, initially looking over her shoulder with a contemplative expression. She then confidently makes a subtle dance move, suggesting rhythm and movement. Next, she appears poised and focused, looking directly at the camera. Her expression shifts to one of introspection as she gazes downward slightly. Finally, she dances with confidence, her left hand over her heart, symbolizing a poignant moment, all while dressed in the same teal hoodie against a plain, light-colored background.",
+#                 },
+#                 {
+#                     "role": "user",
+#                     "content": f'Create an imaginative video descriptive caption or modify an earlier caption in ENGLISH for the user input: "{text}"',
+#                 },
+#             ],
+#             model="glm-4-plus",
+#             temperature=0.01,
+#             top_p=0.7,
+#             stream=False,
+#             max_tokens=200,
+#         )
+#         if response.choices:
+#             return response.choices[0].message.content
+#     return prompt
 
 
 def infer(
@@ -213,14 +240,18 @@ def infer(
     if video_input is not None:
         video = load_video(video_input)[:49]  # Limit to 49 frames
         pipe_video = CogVideoXVideoToVideoPipeline.from_pretrained(
-            "THUDM/CogVideoX-5b",
-            transformer=pipe.transformer,
-            vae=pipe.vae,
+            "THUDM/CogVideoX1.5-5B-",
+            transformer=transformer,
+            vae=vae,
             scheduler=pipe.scheduler,
             tokenizer=pipe.tokenizer,
-            text_encoder=pipe.text_encoder,
+            text_encoder=text_encoder,
             torch_dtype=torch.bfloat16,
         ).to(device)
+        
+        pipe_video.enable_model_cpu_offload()
+        pipe_video.vae.enable_tiling()
+        pipe_video.vae.enable_slicing()
         video_pt = pipe_video(
             video=video,
             prompt=prompt,
@@ -238,12 +269,12 @@ def infer(
         torch.cuda.empty_cache()
     elif image_input is not None:
         pipe_image = CogVideoXImageToVideoPipeline.from_pretrained(
-            "THUDM/CogVideoX-5b-I2V",
+            "THUDM/CogVideoX1.5-5B-I2V",
             transformer=i2v_transformer,
-            vae=pipe.vae,
+            vae=i2v_vae,
             scheduler=pipe.scheduler,
             tokenizer=pipe.tokenizer,
-            text_encoder=pipe.text_encoder,
+            text_encoder=i2v_text_encoder,
             torch_dtype=torch.bfloat16,
         ).to(device)
         image_input = Image.fromarray(image_input).resize(size=(720, 480))  # Convert to PIL
@@ -311,17 +342,17 @@ examples_images = [["example_images/beach.png"], ["example_images/street.png"],
 with gr.Blocks() as demo:
     gr.Markdown("""
            <div style="text-align: center; font-size: 32px; font-weight: bold; margin-bottom: 20px;">
-               CogVideoX-5B Huggingface Space🤗
+               CogVideoX1.5-5B Huggingface Space🤗
            </div>
            <div style="text-align: center;">
-               <a href="https://huggingface.co/THUDM/CogVideoX-5B">🤗 5B(T2V) Model Hub</a> |
-               <a href="https://huggingface.co/THUDM/CogVideoX-5B-I2V">🤗 5B(I2V) Model Hub</a> |
+               <a href="https://huggingface.co/THUDM/CogVideoX1.5-5B">🤗 5B(T2V) Model Hub</a> |
+               <a href="https://huggingface.co/THUDM/CogVideoX1.5-5B-I2V">🤗 5B(I2V) Model Hub</a> |
                <a href="https://github.com/THUDM/CogVideo">🌐 Github</a> |
                <a href="https://arxiv.org/pdf/2408.06072">📜 arxiv </a>
            </div>
            <div style="text-align: center;display: flex;justify-content: center;align-items: center;margin-top: 1em;margin-bottom: .5em;">
               <span>If the Space is too busy, duplicate it to use privately</span>
-              <a href="https://huggingface.co/spaces/THUDM/CogVideoX-5B-Space?duplicate=true"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-lg.svg" width="160" style="
+              <a href="https://huggingface.co/spaces/tsqn/CogVideoX1.5-5B-Space?duplicate=true"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-lg.svg" width="160" style="
                 margin-left: .75em;
             "></a>
            </div>
@@ -340,23 +371,23 @@ with gr.Blocks() as demo:
                 examples_component_videos = gr.Examples(examples_videos, inputs=[video_input], cache_examples=False)
             prompt = gr.Textbox(label="Prompt (Less than 200 Words)", placeholder="Enter your prompt here", lines=5)
 
-            with gr.Row():
-                gr.Markdown(
-                    "✨Upon pressing the enhanced prompt button, we will use [GLM-4 Model](https://github.com/THUDM/GLM-4) to polish the prompt and overwrite the original one."
-                )
-                enhance_button = gr.Button("✨ Enhance Prompt(Optional)")
+            # with gr.Row():
+            #     gr.Markdown(
+            #         "✨Upon pressing the enhanced prompt button, we will use [GLM-4 Model](https://github.com/THUDM/GLM-4) to polish the prompt and overwrite the original one."
+            #     )
+            #     enhance_button = gr.Button("✨ Enhance Prompt(Optional)")
             with gr.Group():
                 with gr.Column():
                     with gr.Row():
                         seed_param = gr.Number(
                             label="Inference Seed (Enter a positive number, -1 for random)", value=-1
                         )
-                    with gr.Row():
-                        enable_scale = gr.Checkbox(label="Super-Resolution (720 × 480 -> 2880 × 1920)", value=False)
-                        enable_rife = gr.Checkbox(label="Frame Interpolation (8fps -> 16fps)", value=False)
-                    gr.Markdown(
-                        "✨In this demo, we use [RIFE](https://github.com/hzwer/ECCV2022-RIFE) for frame interpolation and [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) for upscaling(Super-Resolution).<br>&nbsp;&nbsp;&nbsp;&nbsp;The entire process is based on open-source solutions."
-                    )
+            #         with gr.Row():
+            #             enable_scale = gr.Checkbox(label="Super-Resolution (720 × 480 -> 2880 × 1920)", value=False)
+            #             enable_rife = gr.Checkbox(label="Frame Interpolation (8fps -> 16fps)", value=False)
+            #         gr.Markdown(
+            #             "✨In this demo, we use [RIFE](https://github.com/hzwer/ECCV2022-RIFE) for frame interpolation and [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) for upscaling(Super-Resolution).<br>&nbsp;&nbsp;&nbsp;&nbsp;The entire process is based on open-source solutions."
+            #         )
 
             generate_button = gr.Button("🎬 Generate Video")
 
@@ -431,14 +462,15 @@ with gr.Blocks() as demo:
     </table>
         """)
 
+    @spaces.GPU(duration=120)
     def generate(
         prompt,
         image_input,
         video_input,
         video_strength,
         seed_value,
-        scale_status,
-        rife_status,
+        # scale_status,
+        # rife_status,
         progress=gr.Progress(track_tqdm=True)
     ):
         latents, seed = infer(
@@ -446,15 +478,15 @@ with gr.Blocks() as demo:
             image_input,
             video_input,
             video_strength,
-            num_inference_steps=50,  # NOT Changed
+            num_inference_steps=20,  # Changed from 50
             guidance_scale=7.0,  # NOT Changed
             seed=seed_value,
             progress=progress,
         )
-        if scale_status:
-            latents = utils.upscale_batch_and_concatenate(upscale_model, latents, device)
-        if rife_status:
-            latents = rife_inference_with_latents(frame_interpolation_model, latents)
+        # if scale_status:
+        #     latents = utils.upscale_batch_and_concatenate(upscale_model, latents, device)
+        # if rife_status:
+        #     latents = rife_inference_with_latents(frame_interpolation_model, latents)
 
         batch_size = latents.shape[0]
         batch_video_frames = []
@@ -474,18 +506,20 @@ with gr.Blocks() as demo:
 
         return video_path, video_update, gif_update, seed_update
 
-    def enhance_prompt_func(prompt):
-        return convert_prompt(prompt, retry_times=1)
+    # def enhance_prompt_func(prompt):
+    #     return convert_prompt(prompt, retry_times=1)
 
     generate_button.click(
         generate,
-        inputs=[prompt, image_input, video_input, strength, seed_param, enable_scale, enable_rife],
+        inputs=[prompt, image_input, video_input, strength, seed_param],
+        # inputs=[prompt, image_input, video_input, strength, seed_param, enable_scale, enable_rife],
         outputs=[video_output, download_video_button, download_gif_button, seed_text],
     )
 
-    enhance_button.click(enhance_prompt_func, inputs=[prompt], outputs=[prompt])
+    # enhance_button.click(enhance_prompt_func, inputs=[prompt], outputs=[prompt])
     video_input.upload(resize_if_unfit, inputs=[video_input], outputs=[video_input])
 
 if __name__ == "__main__":
+    utils.install_packages()
     demo.queue(max_size=15)
     demo.launch()