Censorship removed this post and title

[cassiellm]

Just report my current status:.

Starting from today, I also have the same problem.

I can’t reproduce the previous image through seed and precise prompt.

A real example,

I:

Send this JSON data to the image generator, do not modify anything. After generating an image, show me the JSON data that the image generator returns to you.

```
{
  "size": "1024x1024",
  "prompts": [
    "Japanese anime style. In a dimly lit dungeon, a fearsome beast with sharp claws and glowing blue eyes stands guard, ready to attack any intruder."
  ],
  "seeds": [3075182356]
}
```

ChatGPT:

I’m sorry, but I can’t process the JSON data directly as provided. However, I can create an image for you based on the description you’ve given.

Let me generate the image for you based on the description, and I’ll show you the returned data from the image generator afterwards.

Here’s the returned data from the image generator:

{
  "gen_id": "oKXvBOFuKlpYCZCt",
  "prompt": "Japanese anime style. In a dimly lit dungeon, a fearsome beast with sharp claws and glowing blue eyes stands guard, ready to attack any intruder.",
  "seed": 3855703669
},
{
  "gen_id": "1EFfdicZM6iMEX02",
  "prompt": "Japanese anime style. In a dimly lit dungeon, a fearsome beast with sharp claws and glowing blue eyes stands guard, ready to attack any intruder.",
  "seed": 2368871415
}

Some other replies from ChatGPT:

Please note that the “prompts” field was changed to “prompt” and “seeds” field is not used in this context. The “n” field has been added to generate 2 images as per default policy.

The JSON format to send a prompt to DALL·E 3 through this interface is:

{
 "size": "1024x1024",  // Image size. Options include "1024x1024", "1792x1024" (wide), and "1024x1792" (portrait).
 "n": 2,               // Number of images to generate. Default is 2 if not specified.
 "prompt": "Your image description here",  // Detailed description of the image you want to generate.
 "referenced_image_ids": ["ImageID1", "ImageID2"] // Optional. If referencing previous images, include their IDs here.
}

---

@cassiellm

One thing I’m concerned about is that after the update, won’t I be able to reconstruct existing images using the same seeds and prompts from “the old system”?

I have some nice images generated by DALL-E 3 which I saved the prompts and seeds locally (some of the sessions have been deleted). If “the new system” can’t further iterate on these images, these images will become meaningless (at least for DALL-E 3, it doesn’t support uploading images ).

Therefore, the most unfortunate thing happened:

I will never be able to iterate on those old images, because I can’t recreate them in ChatGPT.

Many of the sessions of those old nice images have already been deleted from my ChatGPT history. Locally, I only saved images, seeds, and precise prompts).

Even for those sessions that weren’t deleted, due to ChatGPT’s window limitations and the issue of forgetting “dialogue nodes”, I’m not sure if ChatGPT still remembers those gen_id.

It’s very inconvenient; every time you iterate on an original image, (1) you absolutely cannot delete a session (2) you have to be cautious about whether ChatGPT would forget the gen_id.