使用Colab、Google Cloud与Python生图时seed参数报错求助
Google Vertex AI图像生成添加seed参数报错求助
环境配置代码
!pip install --quiet --upgrade --user google-cloud-aiplatform
import IPython import time app = IPython.Application.instance() app.kernel.do_shutdown(True) from google.colab import auth auth.authenticate_user() import vertexai vertexai.init(project="$PROJECT_ID", location = "us-central1") from vertexai.preview.vision_models import ImageGenerationModel model = ImageGenerationModel.from_pretrained("imagegeneration@005") !pip install --upgrade watermark
可正常运行的图像生成代码
response = model.generate_images( prompt = '''A flower.''', number_of_images = 2 )
问题场景
添加seed参数后执行代码时报错:
model.watermark_enabled = False response = model.generate_images( prompt = '''A flower.''', number_of_images = 2, seed = 42 )
错误信息
_InactiveRpcError Traceback (most recent call last) /usr/local/lib/python3.10/dist-packages/google/api_core/grpc_helpers.py in error_remapped_callable(*args, **kwargs) 71 try: ---> 72 return callable_(*args, **kwargs) 73 except grpc.RpcError as exc: 8 frames _InactiveRpcError: <_InactiveRpcError of RPC that terminated with: status = StatusCode.INVALID_ARGUMENT details = "Image generation failed with the following error: Seed is not supported when watermark is enabled." debug_error_string = "UNKNOWN:Error received from peer ipv4:142.250.141.95:443 {created_time:"2024-05-23T14:53:50.497705026+00:00", grpc_status:3, grpc_message:"Image generation failed with the following error: Seed is not supported when watermark is enabled."}" > The above exception was the direct cause of the following exception: InvalidArgument Traceback (most recent call last) /usr/local/lib/python3.10/dist-packages/google/api_core/grpc_helpers.py in error_remapped_callable(*args, **kwargs) 72 return callable_(*args, **kwargs) 73 except grpc.RpcError as exc: ---> 74 raise exceptions.from_grpc_error(exc) from exc 75 76 return error_remapped_callable InvalidArgument: 400 Image generation failed with the following error: Seed is not supported when watermark is enabled.
已尝试的操作
- 添加
model.watermark_enabled = False后重新执行,无效 - 尝试设置
model.watermark_enabled = True,仍失败 - 执行
!pip install --upgrade watermark后重复上述两种设置,问题依旧
寻求解决方法。
内容的提问来源于stack exchange,提问作者Andrew
相关产品推荐
相关产品推荐

