pip install git+https://github.com/huggingface/transformers
pip install qwen-vl-utils

from PIL import Image
import torch
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
from modelscope import snapshot_download
model_dir = "/mnt/workspace/Qwen2-VL-2B-Instruct"
# Load the model in half-precision on the available device(s)
model = Qwen2VLForConditionalGeneration.from_pretrained(model_dir, device_map="auto", torch_dtype = torch.float16)
min_pixels = 256*28*28
max_pixels = 1280*28*28
processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)
messages = [{"role": "user", "content": [{"type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}, {"type": "text", "text": "Describe this image."}]}]
# Preparation for inference
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt")
inputs = inputs.to('cuda')
# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)
print(output_text)

# Messages containing a video and a text query
messages = [{"role": "user", "content": [{"type": "video", "video": "file:///path/to/video1.mp4", 'max_pixels': 360*420, 'fps': 1.0}, {"type": "text", "text": "Describe this video."}]}]
# Preparation for inference
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt")
inputs = inputs.to('cuda')
# Inference
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)
print(output_text)

# diffusers>=0.30.1
# transformers>=0.44.0
# accelerate>=0.33.0 (suggest install from source)
# imageio-ffmpeg>=0.5.1
pip install --upgrade transformers accelerate diffusers imageio-ffmpeg

import torch
from diffusers import CogVideoXPipeline
from diffusers.utils import export_to_video
from modelscope import snapshot_download
model_dir = snapshot_download("ZhipuAI/CogVideoX-5b")
prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical atmosphere of this unique musical performance."
pipe = CogVideoXPipeline.from_pretrained(
    model_dir,
    torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()
video = pipe(
    prompt=prompt,
    num_videos_per_prompt=1,
    num_inference_steps=50,
    num_frames=49,
    guidance_scale=6,
    generator=torch.Generator(device="cuda").manual_seed(42),
).frames[0]
export_to_video(video, "output.mp4", fps=8)