diff --git a/README.md b/README.md
index e2f4eb3..a1e58fa 100644
--- a/README.md
+++ b/README.md
@@ -169,7 +169,7 @@ pip install -r requirements.txt
 > - 有关自动切片的配置在 `bilive.toml` 文件的 `[slice]` 部分。
 > - `auto_slice` 默认为 false, 即不进行自动切片。
 
-MLLM 模型主要用于自动切片后的切片标题生成，此功能默认关闭，如果需要打开请将 `auto_slice` 参数设置为 `true`。其他配置分别有：
+MLLM 模型主要用于自动切片后的切片标题生成，此功能默认关闭，如果需要打开请将 `auto_slice` 参数设置为 `true`，并且写下你自己的 prompt，其他配置分别有：
 - `slice_duration` 以秒为单位设置切片时长（不建议超过 180 秒）。
 - `slice_num` 设置切片数量。
 - `slice_overlap` 设置切片重叠时长。切片采用滑动窗口法处理，细节内容请见 [auto-slice-video](https://github.com/timerring/auto-slice-video)
@@ -178,11 +178,11 @@ MLLM 模型主要用于自动切片后的切片标题生成，此功能默认关
 
 接下来配置模型有关的 `mllm_model` 参数即对应的 api-key，请自行根据链接注册账号并且申请对应 api key，填写在对应的参数中，请注意以下模型只有你在 `mllm_model` 参数中设置的那个模型会生效。
 
-| Company   |       Google        |    智谱        | 阿里云           |
-|----------------|-------------------|------------------|-----------------------|
-| Name   | Gemini-2.0-flash       | GLM-4V-PLUS | Qwen-2.5-72B-Instruct |
-| `mllm_model`   | `gemini`| `zhipu` | `qwen`  |
-| `API key`   | [gemini_api_key](https://aistudio.google.com/app/apikey) | [zhipu_api_key](https://www.bigmodel.cn/invite?icode=shBtZUfNE6FfdMH1R6NybGczbXFgPRGIalpycrEwJ28%3D) | [qwen_api_key](https://bailian.console.aliyun.com/?apiKey=1) |
+| Company   |    Alicloud           |       zhipu        |    Google        |
+|----------------|-----------------------|------------------|-------------------|
+| Name   | Qwen-2.5-72B-Instruct | GLM-4V-PLUS | Gemini-2.0-flash       |
+| `mllm_model`   | `qwen`  | `zhipu` | `gemini` |
+| `API key`   | [qwen_api_key](https://bailian.console.aliyun.com/?apiKey=1) | [zhipu_api_key](https://www.bigmodel.cn/invite?icode=shBtZUfNE6FfdMH1R6NybGczbXFgPRGIalpycrEwJ28%3D) | [gemini_api_key](https://aistudio.google.com/app/apikey) |
 
 
 #### 2.3 Image Generation Model（自动生成视频封面）
@@ -191,8 +191,7 @@ MLLM 模型主要用于自动切片后的切片标题生成，此功能默认关
 > - 有关自动生成视频封面的配置在 `bilive.toml` 文件的 `[cover]` 部分。
 > - `generate_cover` 默认为 false, 即不进行自动生成视频封面。
 
-采用图生图多模态模型，自动获取视频截图并上传风格变换后的视频封面，如需使用本功能，请将 `generate_cover` 参数设置为 `true`。接下来需要配置的参数有 image_gen_model 和对应的 api key，请自行根据链接注册账号并且申请对应 api key，填写在对应的参数中，请注意以下模型只有你在 `image_gen_model` 参数中设置的那个模型会生效。
-
+采用图生图多模态模型，自动获取视频截图并上传风格变换后的视频封面，如需使用本功能，请将 `generate_cover` 参数设置为 `true`，并且写下你自己的 prompt，注意部分模型只支持英文，接下来需要配置的参数有 image_gen_model 和对应的 api key，请自行根据链接注册账号并且申请对应 api key，填写在对应的参数中，请注意以下模型只有你在 `image_gen_model` 参数中设置的那个模型会生效。
 
 | Company     | Model Name                        | `image_gen_model`   | `API Key`                                                                  |
 |--------------|--------------------------------|-------------------|---------------------------------------------------------------------------------|
@@ -208,10 +207,10 @@ MLLM 模型主要用于自动切片后的切片标题生成，此功能默认关
 
 #### 3. 配置上传参数
 
-上传默认参数如下，[]中内容全部自动替换。可以在 `bilive.toml` 中自定义相关配置，映射关键词为 `{artist}`、`{date}`、`{title}`、`{source_link}`，可自行组合删减定制模板：
+在 `bilive.toml` 中自定义相关配置，映射关键词为 `{artist}`、`{date}`、`{title}`、`{source_link}`，请自行组合删减定制模板：
 
-- `title` 标题模板是`{artist}直播回放-{date}-{title}`，效果为"【弹幕+字幕】[XXX]直播回放-[日期]-[直播间标题]"，可自行修改。
-- `description` 简介模板是`{artist}直播，直播间地址：{source_link} 内容仅供娱乐，直播中主播的言论、观点和行为均由主播本人负责，不代表录播员的观点或立场。`，效果为"【弹幕+字幕】[XXX]直播，直播间地址：[https://live.bilibili.com/XXX] 内容仅供娱乐，直播中主播的言论、观点和行为均由主播本人负责，不代表录播员的观点或立场。"，可自行修改。
+- `title` 标题模板。
+- `description` 简介模板。
 - `gift_price_filter = 1` 表示过滤价格低于 1 元的礼物。
 - `reserve_for_fixing = false` 表示如果视频出现错误，重试失败后不保留视频用于修复，推荐硬盘空间有限的用户设置 false。
 - `upload_line = "auto"` 表示自动探测上传线路并上传，如果需要指定固定的线路，可以设置为 `bldsa`、`ws`、`tx`、`qn`、`bda2`。
diff --git a/bilive.toml b/bilive.toml
index cebf3c0..1516f80 100644
--- a/bilive.toml
+++ b/bilive.toml
@@ -15,10 +15,8 @@ inference_model = "small" # If you choose "deploy", you should download the infe
 
 [video]
 # You can change the title as you like, eg.
-# f"{artist}直播回放-{date}-{title}" - Streamer直播回放-20250328-Live title
-# f"{date}-{artist}直播回放" - 20250328-Streamer直播回放
-title = "{artist}直播回放-{date}-{title}" # Key words: {artist}, {date}, {title}, {source_link}
-description = "{artist}直播回放，直播间地址：{source_link} 内容仅供娱乐，直播中主播的言论、观点和行为均由主播本人负责，不代表录播员的观点或立场。" # Key words: {artist}, {date}, {title}, {source_link}
+title = "{date}直播" # Key words: {artist}, {date}, {title}, {source_link}
+description = "录制请征求主播同意，若未经同意就录制，所引起的任何法律问题均由该违规录制的 b 站账号承担。" # Key words: {artist}, {date}, {title}, {source_link}
 gift_price_filter = 1 # The gift whose price is less than this value will be filtered, unit: RMB
 reserve_for_fixing = false # If encounter MOOV crash error, delete the video or reserve for fixing
 upload_line = "auto" # The upload line to be used, default None is auto detect(recommended), if you want to specify, it can be "bldsa", "ws", "tx", "qn", "bda2".
@@ -30,13 +28,15 @@ slice_num = 2 # the number of slices
 slice_overlap = 30 # the overlap of slices(seconds) see my package https://github.com/timerring/auto-slice-video for more details
 slice_step = 1 # the step of slices(seconds)
 min_video_size = 200 # The minimum video size to be sliced (MB)
-mllm_model = "gemini" # the multi-model LLMs, can be "gemini" or "zhipu" or "qwen"
+mllm_model = "qwen" # the multi-model LLMs, can be "qwen" or "gemini" or "zhipu"
+slice_prompt = "" # Write your own slice prompt here
+qwen_api_key = "" # Apply for your own Qwen API key at https://bailian.console.aliyun.com/?apiKey=1
 zhipu_api_key = "" # Apply for your own GLM-4v-Plus API key at https://www.bigmodel.cn/invite?icode=shBtZUfNE6FfdMH1R6NybGczbXFgPRGIalpycrEwJ28%3D
 gemini_api_key = "" # Apply for your own Gemini API key at https://aistudio.google.com/app/apikey
-qwen_api_key = "" # Apply for your own Qwen API key at https://bailian.console.aliyun.com/?apiKey=1
 
 [cover]
 generate_cover = false # whether to generate cover
+cover_prompt = "" # Write your own cover prompt here
 image_gen_model = "minimax" # the image generation model, can be "minimax" or "siliconflow" or "tencent" or "baidu" or "stability" or "luma" or "ideogram" or "recraft" or "amazon"
 minimax_api_key = "" # Apply for your own Minimax API key at https://platform.minimaxi.com/user-center/basic-information/interface-key
 siliconflow_api_key = "" # Apply for your own SiliconFlow API key at https://cloud.siliconflow.cn/i/3Szr5BVg
diff --git a/src/autoslice/mllm_sdk/gemini_new_sdk.py b/src/autoslice/mllm_sdk/gemini_new_sdk.py
index 24b5052..31e0ed2 100644
--- a/src/autoslice/mllm_sdk/gemini_new_sdk.py
+++ b/src/autoslice/mllm_sdk/gemini_new_sdk.py
@@ -1,7 +1,7 @@
 from google import genai
 from google.genai import types 
 from src.log.logger import scan_log
-from src.config import GEMINI_API_KEY
+from src.config import GEMINI_API_KEY, SLICE_PROMPT
 
 def gemini_generate_title(video_path, artist):
 
@@ -14,7 +14,7 @@ def gemini_generate_title(video_path, artist):
         model='models/gemini-2.0-flash',
         contents=types.Content(
             parts=[
-                types.Part(text=f'视频是{artist}的直播的切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，只需要返回一个标题即可，无需返回其他内容，标题中不要有表情符号。'),
+                types.Part(text=SLICE_PROMPT),
                 types.Part(
                     inline_data=types.Blob(data=video_bytes, mime_type='video/mp4')
                 )
@@ -22,6 +22,6 @@ def gemini_generate_title(video_path, artist):
         )
     )
     scan_log.info("使用 Gemini-2.0-flash 生成切片标题")
-    scan_log.info(f"Prompt: 视频是{artist}的直播的切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，只需要返回一个标题即可，无需返回其他内容，标题中不要有表情符号。")
+    scan_log.info(f"Prompt: {SLICE_PROMPT}")
     scan_log.info(f"生成的切片标题为: {response.text}")
     return response.text
\ No newline at end of file
diff --git a/src/autoslice/mllm_sdk/gemini_old_sdk.py b/src/autoslice/mllm_sdk/gemini_old_sdk.py
index 604c1e1..ba204d4 100644
--- a/src/autoslice/mllm_sdk/gemini_old_sdk.py
+++ b/src/autoslice/mllm_sdk/gemini_old_sdk.py
@@ -1,5 +1,5 @@
 import google.generativeai as genai
-from src.config import GEMINI_API_KEY
+from src.config import GEMINI_API_KEY, SLICE_PROMPT
 from src.log.logger import scan_log
 import time
 
@@ -22,7 +22,7 @@ def gemini_generate_title(video_path, artist):
         raise ValueError(video_file.state.name)
 
     # Create the prompt.
-    prompt = f"视频是{artist}的直播的切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，只返回该标题即可，无需返回其他内容，标题中不要有表情符号。"
+    prompt = SLICE_PROMPT
 
     # Set the model to Gemini Flash.
     model = genai.GenerativeModel(model_name="models/gemini-2.0-flash")
@@ -32,6 +32,6 @@ def gemini_generate_title(video_path, artist):
     # delete the video file
     genai.delete_file(video_file.name)
     scan_log.info("使用 Gemini-2.0-flash 生成切片标题")
-    scan_log.info(f"Prompt: 视频是{artist}的直播的切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，只需要返回一个标题即可，无需返回其他内容，标题中不要有表情符号。")
+    scan_log.info(f"Prompt: {SLICE_PROMPT}")
     scan_log.info(f"生成的切片标题为: {response.text}")
     return response.text
\ No newline at end of file
diff --git a/src/autoslice/mllm_sdk/qwen_sdk.py b/src/autoslice/mllm_sdk/qwen_sdk.py
index a7f4c36..09f1525 100644
--- a/src/autoslice/mllm_sdk/qwen_sdk.py
+++ b/src/autoslice/mllm_sdk/qwen_sdk.py
@@ -1,4 +1,4 @@
-from src.config import QWEN_API_KEY
+from src.config import QWEN_API_KEY, SLICE_PROMPT
 from src.log.logger import scan_log
 from openai import OpenAI
 import os
@@ -28,12 +28,12 @@ def qwen_generate_title(video_path, artist):
                         "type": "video_url",
                         "video_url": {"url": f"data:video/mp4;base64,{base64_video}"},
                     },
-                    {"type": "text", "text": f"视频是{artist}的直播切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，标题中不要表情符号，可以适当使用网络热词或流行语"},
+                    {"type": "text", "text": SLICE_PROMPT},
                 ],
             }
         ],
     )
     scan_log.info("使用 Qwen-2.5-72B-Instruct 生成切片标题")
-    scan_log.info(f"Prompt: 视频是{artist}的直播切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，标题中不要表情符号，可以适当使用网络热词或流行语")
+    scan_log.info(f"Prompt: {SLICE_PROMPT}")
     scan_log.info(f"生成的切片标题为: {completion.choices[0].message.content}")
     return completion.choices[0].message.content.strip('"')
diff --git a/src/autoslice/mllm_sdk/zhipu_sdk.py b/src/autoslice/mllm_sdk/zhipu_sdk.py
index 28c9835..ba1cf64 100644
--- a/src/autoslice/mllm_sdk/zhipu_sdk.py
+++ b/src/autoslice/mllm_sdk/zhipu_sdk.py
@@ -1,7 +1,7 @@
 # Copyright (c) 2024 bilive.
 
 import base64
-from src.config import ZHIPU_API_KEY
+from src.config import ZHIPU_API_KEY, SLICE_PROMPT
 from zhipuai import ZhipuAI
 from src.log.logger import scan_log
 
@@ -24,13 +24,13 @@ def zhipu_glm_4v_plus_generate_title(video_path, artist):
             },
             {
                 "type": "text",
-                "text": f"视频是{artist}的直播的切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，注意标题中如果有“主播”请替换成{artist}"
+                "text": SLICE_PROMPT
             }
             ]
         }
         ]
     )
     scan_log.info("使用 Zhipu-glm-4v-plus 生成切片标题")
-    scan_log.info(f"Prompt: 视频是{artist}的直播的切片，请根据该视频中的内容及弹幕信息，为这段视频起一个调皮并且吸引眼球的标题，注意标题中如果有“主播”请替换成{artist}")
+    scan_log.info(f"Prompt: {SLICE_PROMPT}")
     scan_log.info(f"生成的切片标题为: {response.choices[0].message.content}")
     return response.choices[0].message.content.replace("《", "").replace("》", "")
\ No newline at end of file
diff --git a/src/config.py b/src/config.py
index 2788b6d..ffce9d5 100644
--- a/src/config.py
+++ b/src/config.py
@@ -85,3 +85,6 @@ IDEOGRAM_API_KEY = config.get('cover', {}).get('ideogram_api_key')
 RECRAFT_API_KEY = config.get('cover', {}).get('recraft_api_key')
 AWS_ACCESS_KEY_ID = config.get('cover', {}).get('aws_access_key_id')
 AWS_SECRET_ACCESS_KEY = config.get('cover', {}).get('aws_secret_access_key')
+
+SLICE_PROMPT = config.get('slice', {}).get('slice_prompt')
+COVER_PROMPT = config.get('cover', {}).get('cover_prompt')
\ No newline at end of file
diff --git a/src/cover/image_model_sdk/amazon_sdk.py b/src/cover/image_model_sdk/amazon_sdk.py
index 4fb560a..7381fc4 100644
--- a/src/cover/image_model_sdk/amazon_sdk.py
+++ b/src/cover/image_model_sdk/amazon_sdk.py
@@ -12,7 +12,7 @@ from PIL import Image
 from botocore.exceptions import ClientError
 import os
 import time
-from src.config import AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY
+from src.config import AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, COVER_PROMPT
 
 class ImageError(Exception):
     "Custom exception for errors returned by Amazon Titan Image Generator V2"
@@ -67,7 +67,7 @@ def amazon_generate_cover(your_file_path):
         body = json.dumps({
             "taskType": "TEXT_IMAGE",
             "textToImageParams": {
-                "text": "This is a video screenshot, please generate a cover in the style of a manga",
+                "text": COVER_PROMPT,
                 "negativeText": "",
                 "conditionImage": input_image,
                 "controlMode": "CANNY_EDGE"
diff --git a/src/cover/image_model_sdk/baidu_sdk.py b/src/cover/image_model_sdk/baidu_sdk.py
index 3728a00..9de52a3 100644
--- a/src/cover/image_model_sdk/baidu_sdk.py
+++ b/src/cover/image_model_sdk/baidu_sdk.py
@@ -6,7 +6,7 @@ from PIL import Image
 from io import BytesIO
 import time
 from src.upload.bilitool.bilitool.model.model import Model
-from src.config import BAIDU_API_KEY
+from src.config import BAIDU_API_KEY, COVER_PROMPT
 
 
 def cover_up(img: str):
@@ -72,7 +72,7 @@ def baidu_generate_cover(your_file_path):
         payload = json.dumps(
             {
                 "model": "irag-1.0",
-                "prompt": "这是视频截图，请根据该图生成对应的动漫类型的封面",
+                "prompt": COVER_PROMPT,
                 "refer_image": cover_url,
             }
         )
diff --git a/src/cover/image_model_sdk/ideogram_sdk.py b/src/cover/image_model_sdk/ideogram_sdk.py
index 28bafae..58d20bf 100644
--- a/src/cover/image_model_sdk/ideogram_sdk.py
+++ b/src/cover/image_model_sdk/ideogram_sdk.py
@@ -2,7 +2,7 @@ import requests
 import json
 import os
 import time
-from src.config import IDEOGRAM_API_KEY
+from src.config import IDEOGRAM_API_KEY, COVER_PROMPT
 
 
 def ideogram_generate_cover(your_file_path):
@@ -19,7 +19,7 @@ def ideogram_generate_cover(your_file_path):
         payload = {
             "image_request": json.dumps(
                 {
-                    "prompt": "This is a video screenshot, please generate a cover in the style of a manga",
+                    "prompt": COVER_PROMPT,
                     "aspect_ratio": "ASPECT_10_16",
                     "image_weight": 75,
                     "magic_prompt_option": "ON",
diff --git a/src/cover/image_model_sdk/kolors_sdk.py b/src/cover/image_model_sdk/kolors_sdk.py
index 1e590ef..6ba2fef 100644
--- a/src/cover/image_model_sdk/kolors_sdk.py
+++ b/src/cover/image_model_sdk/kolors_sdk.py
@@ -2,7 +2,7 @@ import requests
 import base64
 import time
 import os
-from src.config import SILICONFLOW_API_KEY
+from src.config import SILICONFLOW_API_KEY, COVER_PROMPT
 
 
 def kolors_generate_cover(your_file_path):
@@ -17,7 +17,7 @@ def kolors_generate_cover(your_file_path):
 
     payload = {
         "model": "Kwai-Kolors/Kolors",
-        "prompt": "这是一个视频截图，请尝试生成对应的日本动漫类型的封面",
+        "prompt": COVER_PROMPT,
         "image_size": "1024x1024",
         "batch_size": 1,
         "num_inference_steps": 20,
diff --git a/src/cover/image_model_sdk/luma_sdk.py b/src/cover/image_model_sdk/luma_sdk.py
index aa20567..0152567 100644
--- a/src/cover/image_model_sdk/luma_sdk.py
+++ b/src/cover/image_model_sdk/luma_sdk.py
@@ -7,7 +7,7 @@ from PIL import Image
 from io import BytesIO
 from lumaai import LumaAI
 from src.upload.bilitool.bilitool.model.model import Model
-from src.config import LUMA_API_KEY
+from src.config import LUMA_API_KEY, COVER_PROMPT
 
 
 def cover_up(img: str):
@@ -72,7 +72,7 @@ def luma_generate_cover(your_file_path):
             auth_token=LUMA_API_KEY,
         )
         generation = client.generations.image.create(
-            prompt="This is a video screenshot, please generate a cover in the style of a manga",
+            prompt=COVER_PROMPT,
             image_ref=[{"url": cover_url, "weight": 0.85}],
         )
         completed = False
diff --git a/src/cover/image_model_sdk/minimax_sdk.py b/src/cover/image_model_sdk/minimax_sdk.py
index 1db6438..5017422 100644
--- a/src/cover/image_model_sdk/minimax_sdk.py
+++ b/src/cover/image_model_sdk/minimax_sdk.py
@@ -3,7 +3,7 @@ import json
 import base64
 import os
 import time
-from src.config import MINIMAX_API_KEY
+from src.config import MINIMAX_API_KEY, COVER_PROMPT
 
 
 def minimax_generate_cover(your_file_path):
@@ -20,7 +20,7 @@ def minimax_generate_cover(your_file_path):
     payload = json.dumps(
         {
             "model": "image-01",
-            "prompt": "这是一个视频截图，请生成其对应的吉普力风格的图片",
+            "prompt": COVER_PROMPT,
             "subject_reference": [
                 {"type": "character", "image_file": f"data:image/jpeg;base64,{data}"}
             ],
diff --git a/src/cover/image_model_sdk/recraft_sdk.py b/src/cover/image_model_sdk/recraft_sdk.py
index 04663ed..7c06443 100644
--- a/src/cover/image_model_sdk/recraft_sdk.py
+++ b/src/cover/image_model_sdk/recraft_sdk.py
@@ -1,5 +1,5 @@
 from openai import OpenAI
-from src.config import RECRAFT_API_KEY
+from src.config import RECRAFT_API_KEY, COVER_PROMPT
 import requests
 import os
 import time
@@ -20,7 +20,7 @@ def recraft_generate_cover(your_file_path):
                 'image': open(your_file_path, 'rb'),
             },
             body={
-                'prompt': 'This is a video screenshot, please generate a cover in the style of a manga',
+                'prompt': COVER_PROMPT,
                 'strength': 0.75,
             },
         )
diff --git a/src/cover/image_model_sdk/stability_sdk.py b/src/cover/image_model_sdk/stability_sdk.py
index c724209..9e907d1 100644
--- a/src/cover/image_model_sdk/stability_sdk.py
+++ b/src/cover/image_model_sdk/stability_sdk.py
@@ -1,5 +1,5 @@
 import requests
-from src.config import STABILITY_API_KEY
+from src.config import STABILITY_API_KEY, COVER_PROMPT
 import time
 import os
 
@@ -24,7 +24,7 @@ def stable_diffusion_generate_cover(your_file_path):
             },
             files={"image": ("image.jpg", img_file, "image/jpeg")},
             data={
-                "prompt": "This is a video screenshot, please generate a cover in the style of a manga",  # English only
+                "prompt": COVER_PROMPT,  # English only
                 "strength": 0.75,
                 "output_format": "jpeg",
                 "mode": "image-to-image",
diff --git a/src/cover/image_model_sdk/tencent_sdk.py b/src/cover/image_model_sdk/tencent_sdk.py
index 63fefa2..f780ec9 100644
--- a/src/cover/image_model_sdk/tencent_sdk.py
+++ b/src/cover/image_model_sdk/tencent_sdk.py
@@ -8,7 +8,7 @@ import base64
 from datetime import datetime
 import os
 import requests
-from src.config import TENCENT_SECRET_ID, TENCENT_SECRET_KEY
+from src.config import TENCENT_SECRET_ID, TENCENT_SECRET_KEY, COVER_PROMPT
 
 if sys.version_info[0] <= 2:
     from httplib import HTTPSConnection
@@ -125,7 +125,7 @@ def hunyuan_generate_cover(your_file_path):
     submit_action = "SubmitHunyuanImageJob"
     with open(your_file_path, "rb") as image_file:
         data = base64.b64encode(image_file.read()).decode("utf-8")
-    payload = f'{{"Prompt":"这是一个视频截图，请尝试根据该图生成对应的动漫类型的封面","Style":"riman","ContentImage":{{"ImageBase64":"data:image/png;base64,{data}"}}}}'
+    payload = f'{{"Prompt":"{COVER_PROMPT}","Style":"riman","ContentImage":{{"ImageBase64":"data:image/png;base64,{data}"}}}}'
     submit_return = post_request(submit_action, payload).decode("utf-8")
     job_id = json.loads(submit_return)["Response"]["JobId"]
     query_action = "QueryHunyuanImageJob"
diff --git a/src/upload/extract_video_info.py b/src/upload/extract_video_info.py
index 444b2c9..d85f236 100644
--- a/src/upload/extract_video_info.py
+++ b/src/upload/extract_video_info.py
@@ -46,17 +46,15 @@ def generate_title(video_path):
         upload_log.error(f"Error occurred in generate_title: {title}")
         return None
     source_link = generate_source(video_path)
-    prefix = "【弹幕+字幕】"
     formatted_title = TITLE.format(artist=artist, date=date, title=title, source_link=source_link)
-    new_title = f"{prefix}{formatted_title}"
+    new_title = f"{formatted_title}"
     return new_title
 
 def generate_desc(video_path):
     title, artist, date = get_video_info(video_path)
     source_link = generate_source(video_path)
-    prefix = "【弹幕+字幕】"
     formatted_desc = DESC.format(artist=artist, date=date, title=title, source_link=source_link)
-    new_desc = f"{prefix}{formatted_desc}"
+    new_desc = f"{formatted_desc}"
     return new_desc
 
 def generate_tag(video_path):