Login with your OpenAI/DALL-E 2 account here:
Copy the Key and go to the plugin panel, Click on “Add “DALL-E 2”
In Configuration paste that key from Clipboard.
Please make sure that you your billing: https://beta.openai.com/account/billing/overview
Existing DALL-E 2 credits will be ignored.
The main panel offers access to different configurations in top menu and also offers buttons for each functions:
Prompt: enter whatever you want to see in text input (e.g. "a cat in suit" or just “ a duck” like in the screenshot).
Please check the DALL·E - Content Policy FAQ So there might be an unexpected error coming up from the DALL-E 2 content filter.
We have separated the so called modifiers from main prompt input. And so you can define modifiers for individual styles below prompt input. You can also manage your own library with modifiers. Each list of modifiers can be assigned to tags which can be selected at the top as category:
Switch to Modifier ideas for a quick selection of styles:
So with that separation you can quickly change the style of a prompt with manually typing or copy/paste a long string again.
We also implemented to comment out a line in modifier box:
In this example "pastel colored" will not be part of the full prompt.
Number of images: generate between 1 and 4 images. DALL-E 2 has not all the properties of Stable-Diffusion but also offers great results.
In the main panel all image generation tasks are shown. Also multiple tasks can be started for DALL-E 2 at the same time.
Note: The task list is only temporary and will be empty after Photoshop or plugin restart.
Please keep beta limitations in mind, from the OpenAI guide: “The Images API is in beta. During this time the API and models will evolve based on your feedback. To ensure all users can prototype comfortably, the default rate limit is 10 images per minute, 25 per 5 minutes. If you would like to increase your rate limit, please review this help center article. We will increase the default rate limit as we learn more about usage and capacity requirements.”
After starting image Generation you will see a preview window. Here you can select an
The following example (“dinosaur having an important business meeting, stock photography, highly detailed”) shows also the powerful capabilities to generate more complex scenes:
Click On “layer Preview” for Inline-Preview of images on canvas:
Now you can browse through the images and Select the current one as well.
For this preview a temporary layer group “_ai” will be generated.
The image at selection is used as the basis for variations of it. There are no parameters in this mode and no text prompt is asked. Only the selected images will be used for this feature.
With Inpainting a part of an existing image can be changed. There are the following variations of this technique in DALLE-2 supported:
1. Normal Inpainting
First remove a part of an image. Then make a selection big enough that AI can
understand the surroundings and close enough to have good resolution. Also the erased part should match the
prompt. Otherwise the object in Inpaint might be cut off at the edges or not shown at all.
Note: make sure to use a hard (100% hardness) eraser in pencil mode here otherwise you will get weird black border:
DALL-E 2 offers state-of-the-art Outpainting. But it has the same limitations because it uses only a part of an image for extending it. So it does not know the whole context.
To keep a consistent image:
It is a variation of Outpainting where three or four sides will be extended which works fine with that large image size of DALL-E 2. A common example is to use a previous generated close-up of a face/head and scale it down to around ⅓ and do Outpainting of all 4 sides to get more of the body and background.
Use 1024x1024 (recommend) or 512x512
There is a bug in Photoshop which does not allow image operations while having a dialog open. So it is recommended to check this box if you are using a M1 Mac.