基于 EasyAnimate 模型的视频生成最佳实践

project/├── datasets/│   ├── internal_datasets/│       ├── videos/│       │   ├── 00000001.mp4│       │   ├── 00000002.mp4│       │   └── .....│       └── json_of_internal_datasets.json

[    {      "file_path": "videos/00000001.mp4",      "text": "A group of young men in suits and sunglasses are walking down a city street.",      "type": "video"    },    {      "file_path": "videos/00000002.mp4",      "text": "A notepad with a drawing of a woman on it.",      "type": "video"    }    .....]

export DATASET_NAME=“” # 训练数据所在目录export DATASET_META_NAME=“datasets/Minimalism/metadata_add_width_height.json” # 训练文件地址

import jsonimport requests

def post_diffusion_transformer(diffusion_transformer_path, url='http://127.0.0.1:7860', token=None):    datas = json.dumps({        "diffusion_transformer_path": diffusion_transformer_path    })    head = {        'Authorization': token    }    r = requests.post(f'{url}/easyanimate/update_diffusion_transformer', data=datas, headers=head, timeout=15000)    data = r.content.decode('utf-8')    return data
def post_update_edition(edition, url='http://0.0.0.0:7860',token=None):    head = {        'Authorization': token    }
    datas = json.dumps({        "edition": edition    })    r = requests.post(f'{url}/easyanimate/update_edition', data=datas, headers=head)    data = r.content.decode('utf-8')    return data  if __name__ == '__main__':    url = '<eas-service-url>'    token = '<eas-service-token>'
    # -------------------------- #    #  Step 1: update edition    # -------------------------- #    edition = "v2"    outputs = post_update_edition(edition,url = url,token=token)    print('Output update edition: ', outputs)
    # -------------------------- #    #  Step 2: update edition    # -------------------------- #    # 默认路径不可修改    diffusion_transformer_path = "/mnt/models/Diffusion_Transformer/EasyAnimateV2-XL-2-512x512"    outputs = post_diffusion_transformer(diffusion_transformer_path, url = url, token=token)    print('Output update edition: ', outputs)

import base64import jsonimport sysimport timefrom datetime import datetimefrom io import BytesIO
import cv2import requestsimport base64

def post_infer(is_image, length_slider, url='http://127.0.0.1:7860',token=None):    head = {        'Authorization': token    }
    datas = json.dumps({        "base_model_path": "none",        "motion_module_path": "none",        "lora_model_path": "none",         "lora_alpha_slider": 0.55,         "prompt_textbox": "This video shows Mount saint helens, washington - the stunning scenery of a rocky mountains during golden hours - wide shot. A soaring drone footage captures the majestic beauty of a coastal cliff, its red and yellow stratified rock faces rich in color and against the vibrant turquoise of the sea.",         "negative_prompt_textbox": "Strange motion trajectory, a poor composition and deformed video, worst quality, normal quality, low quality, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera",         "sampler_dropdown": "Euler",         "sample_step_slider": 30,         "width_slider": 672,         "height_slider": 384,         "is_image": is_image,        "length_slider": length_slider,        "cfg_scale_slider": 6,        "seed_textbox": 43,    })    r = requests.post(f'{url}/easyanimate/infer_forward', data=datas, headers=head,timeout=1500)    data = r.content.decode('utf-8')    return data
if __name__ == '__main__':    # initiate time    now_date    = datetime.now()    time_start  = time.time()          url = '<eas-service-url>'    token = '<eas-service-token>'
    # -------------------------- #    #  Step 3: infer    # -------------------------- #    is_image = False    length_slider = 27    outputs = post_infer(is_image, length_slider, url = url, token=token)        # Get decoded data    outputs = json.loads(outputs)    base64_encoding = outputs["base64_encoding"]    decoded_data = base64.b64decode(base64_encoding)
    if is_image or length_slider == 1:        file_path = "1.png"    else:        file_path = "1.mp4"    with open(file_path, "wb") as file:        file.write(decoded_data)            # End of record time    time_end = time.time()      time_sum = (time_end - time_start) % 60     print('# --------------------------------------------------------- #')    print(f'#   Total expenditure: {time_sum}s')    print('# --------------------------------------------------------- #')