Hey i’ve been building something that asks the chat to generate images while connected to my app in Dev mode but it claims it doesn’t have access to the image generation tool.
Does anyone know if Is this just a dev-mode issue or if this is intended and meant to be the same in production?
Hey, having the same issue here!
My use case: the user uploads a photo of their apartment into the conversation , and my MCP tool searches a product catalog to find a matching piece of furniture. I then pass the furniture image into the context of the LLM using the uploadFiles API, and I want the model to generate a new image that projects the furniture piece into the user’s apartment.
Looks like in production it works fine but in Developer Mode the model just refuses to generate an image. This kind of “see it in your room” experience is something my client wants, but right now there’s no way to develop it properly.
Is there any timeline on enabling image generation in Developer Mode? Or a potential workaround @OpenAI_Support