Open Feiyuyu0503 opened 6 months ago
👀 @Feiyuyu0503
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible. Please make sure you have given us as much context as possible.\ 非常感谢您提交 issue。我们会尽快调查此事,并尽快回复您。 请确保您已经提供了尽可能多的背景信息。
希望可以把dall e 功能改成可以配置的变量,因为我是多人使用,这个太贵了不希望开启
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
I hope that the dall e function can be changed into a configurable variable, because I use it with multiple people and it is too expensive and I don’t want to enable it.
是的,画图应该成为一个通用的功能,就行 OpenAI 的 chat 对话一样,而不只是 dall-e-3。
应该不少用户都使用了 one-api,其中不少服务都支持画图功能,例如 ChatGLM,阿里的通义千问等。
@tisfeng 后续应该不太可能说对接 one-api 的画图能力。但是会考虑将 image 生成做成 AgentRuntime 的通用方法
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
@tisfeng It is unlikely that we will talk about the drawing capabilities of one-api in the future. But we will consider making image generation into a common method of AgentRuntime.
🥰 需求描述 | Feature Description
是否有可能将这里的'dall-e-3'变成可配置模型名呢? https://github.com/lobehub/lobe-chat/blob/dc7642d8dea5d2ac04a79aa394c540e560b5d642/src/services/imageGeneration.ts#L11 因为我使用的api已经将其他绘画模型的调用适配成openai image generation的格式,https:///v1/image/generations,但是只支持包括sd等的其他绘画模型,不支持dall-e-3
🧐 解决方案 | Proposed Solution
增加图像生成的配置项
📝 补充信息 | Additional Information
No response