timerring · timerring · Apr 12, 2025 · Apr 12, 2025 · Apr 12, 2025 · Apr 12, 2025
diff --git a/README.md b/README.md
@@ -32,6 +32,7 @@
   <img src="assets/ideogram.svg" alt="Ideogram V_2" width="50" height="60" />
   <img src="assets/recraft.svg" alt="Recraft" width="50" height="60" />
   <img src="assets/aws-color.svg" alt="Amazon" width="50" height="60" />
+  <img src="assets/hidream-color.svg" alt="Hidream I1" width="100" height="60" />
 </div>
 
 ##  1. Introduction
@@ -70,10 +71,12 @@
   - `Ideogram V_2`
   - `Recraft`
   - `Amazon Titan Image Generator V2`
+  - `Hidream I1`
+
 
 项目架构流程如下：
 
-![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-12-14-46-16.png)
+![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-12-17-04-11.png)
 
 ## 3. 测试硬件
 
@@ -207,6 +210,7 @@ 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
 | Ideogram     | Ideogram V_2                   | `ideogram`          | [ideogram_api_key](https://ideogram.ai/manage-api)                              |
 | Recraft      | Recraft V3                       | `recraft`           | [recraft_api_key](https://www.recraft.ai/profile/api)                           |
 | Amazon       | Titan Image Generator V2                        | `amazon`            | [aws_access_key_id and aws_secret_access_key](https://aws.amazon.com/console/)                               |
+| Hidream      | Hidream I1                       | `hidream`            | [hidream_api_key](https://www.hidreamai.com/platform/token)                               |
 
 #### 3. 配置上传参数
 

diff --git a/assets/hidream-color.svg b/assets/hidream-color.svg
diff --git a/bilive.toml b/bilive.toml
@@ -30,7 +30,7 @@ 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 = "qwen" # the multi-model LLMs, can be "qwen" or "gemini" or "zhipu"
+mllm_model = "qwen" # the multi-model LLMs, can be "qwen" or "gemini" or "zhipu" or "sensenova"
 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
@@ -39,7 +39,7 @@ sensenova_api_key = "" # Apply for your own SenseNova API key at https://console
 [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"
+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" or "hidream"
 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
 tencent_secret_id = "" # Apply for your own Tencent Cloud API key at https://console.cloud.tencent.com/cam/capi
@@ -50,4 +50,5 @@ luma_api_key = "" # Apply for your own Luma API key at https://lumalabs.ai/api/k
 ideogram_api_key = "" # Apply for your own Ideogram API key at https://ideogram.ai/manage-api
 recraft_api_key = "" # Apply for your own Recraft API key at https://www.recraft.ai/profile/api
 aws_access_key_id = "" # Apply for your own AWS access key id at https://aws.amazon.com/console/
-aws_secret_access_key = "" # Apply for your own AWS secret access key as above
+aws_secret_access_key = "" # Apply for your own AWS secret access key as above
+hidream_api_key = "" # Apply for your own Hidream API key at https://www.hidreamai.com/platform/token
diff --git a/docs/getting-started.md b/docs/getting-started.md
@@ -36,4 +36,4 @@ Automatically monitors and records Bilibili live broadcasts and danmaku (includi
 
 The project architecture process is as follows:
 
-![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-12-14-46-16.png)
+![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-12-17-04-11.png)
diff --git a/src/config.py b/src/config.py
@@ -91,6 +91,7 @@ def get_interface_config():
 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")
+HIDREAM_API_KEY = config.get("cover", {}).get("hidream_api_key")
 
 SLICE_PROMPT = config.get("slice", {}).get("slice_prompt")
 COVER_PROMPT = config.get("cover", {}).get("cover_prompt")
diff --git a/src/cover/cover_generator.py b/src/cover/cover_generator.py
@@ -89,6 +89,10 @@ def wrapper(video_path):
                 from .image_model_sdk.amazon_sdk import amazon_generate_cover
 
                 return amazon_generate_cover(cover_path)
+            elif model_type == "hidream":
+                from .image_model_sdk.hidream_sdk import hidream_generate_cover
+
+                return hidream_generate_cover(cover_path)
             else:
                 upload_log.error(f"Unsupported model type: {model_type}")
                 return None

diff --git a/src/cover/image_model_sdk/hidream_sdk.py b/src/cover/image_model_sdk/hidream_sdk.py
@@ -0,0 +1,79 @@
+import requests
+import json
+import uuid
+import base64
+from src.config import HIDREAM_API_KEY, COVER_PROMPT
+
+def get_image_base64(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+def _get_task_id(image_path):
+    image_base64 = get_image_base64(image_path)
+    headers = {
+        'Authorization': f'Bearer {HIDREAM_API_KEY}',
+        'Content-Type': 'application/json',
+        'API-User-ID': ''
+    }
+
+    data = {
+        "image": image_base64,
+        "prompt": COVER_PROMPT,
+        "negative_prompt": "sun",
+        "img_count": 1,
+        "version": "v1",
+        "resolution": "2048*2048",
+        "request_id": str(uuid.uuid4())
+    }
+
+    url = 'https://www.hidreamai.com/api-pub/gw/v3/image/img2img/async'
+    response = requests.post(url, headers=headers, data=json.dumps(data))
+
+    if response.status_code == 200:
+        if response.json()['code'] == 0:
+            task_id = response.json()['result']['task_id']
+            return task_id
+        else:
+            print(response.json()['message'])
+            return None
+    else:
+        print(response.status_code)
+        return None
+
+def hidream_generate_cover(your_file_path):
+    task_id = _get_task_id(your_file_path)
+    if task_id:
+        headers = {
+            'Authorization': f'Bearer {HIDREAM_API_KEY}'
+        }
+
+        params = {
+            'task_id': task_id,
+            'request_id': ''
+        }
+
+        url = 'https://www.hidreamai.com/api-pub/gw/v3/image/img2img/async/results'
+        response = requests.get(url, headers=headers, params=params)
+
+        if response.status_code == 200:
+            if response.json()['code'] == 0:
+                image_url = response.json()['result']['sub_task_results']['image']
+                img_data = requests.get(image_url).content
+                cover_name = time.strftime("%Y%m%d%H%M%S") + ".jpg"
+                temp_cover_path = os.path.join(os.path.dirname(your_file_path), cover_name)
+                with open(temp_cover_path, "wb") as handler:
+                    handler.write(img_data)
+                os.remove(your_file_path)
+                return temp_cover_path                    
+            else:
+                print(response.json()['message'])
+                return None
+        else:
+            print(response.status_code)
+            return None
+    else:
+        return None
+
+
+if __name__ == "__main__":
+    print(hidream_generate_cover(""))
Original file line number	Diff line number	Diff line change
Expand Up		@@ -36,4 +36,4 @@ Automatically monitors and records Bilibili live broadcasts and danmaku (includi

		The project architecture process is as follows:

		![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-12-14-46-16.png)
		![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-12-17-04-11.png)