add vlm

app.py

@@ -28,6 +28,8 @@ from diffusers import (
 )
 from diffusers.utils import load_video, load_image
 from datetime import datetime, timedelta
+from PIL import Image
+from transformers import AutoModelForCausalLM, LlamaTokenizer
 
 from diffusers.image_processor import VaeImageProcessor
 from openai import OpenAI
@@ -171,55 +173,73 @@ 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
+def convert_prompt(prompt: str, image_path: str = None, retry_times: int = 3) -> str:
+    # Define model and tokenizer paths
+    MODEL_PATH = "THUDM/cogagent-chat-hf"
+    TOKENIZER_PATH = "lmsys/vicuna-7b-v1.5"
+    DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
+    torch_type = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16
+
+    # Initialize model and tokenizer
+    tokenizer = LlamaTokenizer.from_pretrained(TOKENIZER_PATH)
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_PATH,
+        torch_dtype=torch_type,
+        low_cpu_mem_usage=True,
+        trust_remote_code=True
+    ).to(DEVICE).eval()
+
+    # Conversation template for text-only queries
+    text_only_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {} ASSISTANT:"
+    
+    # Check if image is available
+    if image_path and os.path.isfile(image_path):
+        image = Image.open(image_path).convert('RGB')
+    else:
+        image = None
+    
+    # Initialize history for conversation context
+    history = []
+    query = prompt.strip()
+    
+    for _ in range(retry_times):
+        if image is None:
+            # Text-only query, format as required by CogAgent
+            query = text_only_template.format(query)
+            input_by_model = model.build_conversation_input_ids(tokenizer, query=query, history=history, template_version='base')
+            inputs = {
+                'input_ids': input_by_model['input_ids'].unsqueeze(0).to(DEVICE),
+                'token_type_ids': input_by_model['token_type_ids'].unsqueeze(0).to(DEVICE),
+                'attention_mask': input_by_model['attention_mask'].unsqueeze(0).to(DEVICE)
+            }
+        else:
+            # Image-based input with initial query
+            input_by_model = model.build_conversation_input_ids(tokenizer, query=query, history=history, images=[image])
+            inputs = {
+                'input_ids': input_by_model['input_ids'].unsqueeze(0).to(DEVICE),
+                'token_type_ids': input_by_model['token_type_ids'].unsqueeze(0).to(DEVICE),
+                'attention_mask': input_by_model['attention_mask'].unsqueeze(0).to(DEVICE),
+                'images': [[input_by_model['images'][0].to(DEVICE).to(torch_type)]]
+            }
+            if 'cross_images' in input_by_model and input_by_model['cross_images']:
+                inputs['cross_images'] = [[input_by_model['cross_images'][0].to(DEVICE).to(torch_type)]]
+
+        # Generation settings
+        gen_kwargs = {"max_length": 2048, "do_sample": False}
+
+        with torch.no_grad():
+            outputs = model.generate(**inputs, **gen_kwargs)
+            outputs = outputs[:, inputs['input_ids'].shape[1]:]
+            response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+            response = response.split("</s>")[0].strip()  # Clean up response
+
+            if response:
+                return response  # Return the response if generated successfully
+
+    # Return original prompt if all retries fail
     return prompt
 
+
 @spaces.GPU
 def infer(
     prompt: str,
@@ -323,11 +343,11 @@ with gr.Blocks() as demo:
            """)
     with gr.Row():
         with gr.Column():
-            image_in = gr.Image(label="Image Input", type="filepath")
+            image_in = gr.Image(label="Input Image (will be cropped to 720 * 480)")
             examples_component_images = gr.Examples(examples_images, inputs=[image_in], cache_examples=False)
             # prompt = gr.Textbox(label="Prompt")
             orbit_type = gr.Radio(label="Orbit type", choices=["Left", "Up"], value="Left", interactive=True)
-            submit_btn = gr.Button("Submit")
+            # submit_btn = gr.Button("Submit")
 
         # with gr.Column():
             # with gr.Accordion("I2V: Image Input (cannot be used simultaneously with video input)", open=False):
@@ -341,9 +361,9 @@ with gr.Blocks() as demo:
 
             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."
+                    "✨Upon pressing the enhanced prompt button, we will use [CogVLM](https://github.com/THUDM/CogVLM) to polish the prompt and overwrite the original one."
                 )
-                enhance_button = gr.Button("✨ Enhance Prompt(Optional)")
+                enhance_button = gr.Button("✨ Enhance Prompt(Optional but highly recommend)")
             with gr.Group():
                 with gr.Column():
                     with gr.Row():