Skip to main content ↑ ↓
Recent Posts
61
General Discussion / Re: Welcome to AI Image Central!
Last post by Jeff -
Added a new feature to all models that lets you choose the shape of the image of either a rectangle (Original) or a square.

For SD3.5   - Up to 1280x768 rectangle or 1024x1024 square
For Flux      - Up to 960x544 rectangle or 768x768 square
For SDXL    - Up to 1280x768 rectangle or 1024x1024 square

Just click the image of the rectangle or image of the square to switch.

Size matters. Models have limits on how small an image they can produce without artifacts.

Stable Diffusion 3.5 models do not work well for images below 400x400 (Even with CFG set to 1.5).
All the Flux models work well with smaller images even down to 100x100.
All SDXL models work well with smaller images as low as 250x250.
62
General Discussion / Re: Welcome to AI Image Central!
Last post by Jeff -
I had set the search engines to use AI generated descriptions but I don't think this was the best approach as the AI generated
 descriptions seem kind of bland due to issues like recognizing famous people.  So now I have instead created a python script to
 extract the actual prompts from the images to be used by the search engines (Same as prompt under INFO).

I have also fixed the ANY and ALL search engines so that the order of the words does not affect the results.


63
General Discussion / Re: Welcome to AI Image Central!
Last post by Jeff -
I am removing the HiDream model. The quality is not anything special and it's ridiculously slow to load for some reason.
I blame the ComfyUI API but unfortunately there are no other options with this kind of model support.
A1111, Forge, and InvokeAI all useless.
 
64
General Discussion / Re: Welcome to AI Image Central!
Last post by Jeff -
Added custom size (X/Y sliders) option to SDXL.

All SDXL models work well with smaller images as low as 250x250.

Added custom size (X/Y sliders) option to Lumina 2.

Lumina 2 does not work well with images below 500x500.

66
General Discussion / Re: Welcome to AI Image Central!
Last post by Jeff -
I have been working on a new interface that allows you to customize the size of the image.
So far I have only implemented it for the Stable Diffusion 3.5 models.
Let me know how you like it...
Maximum size is 1280x768/768x1280 or 960x544/544x960 depending on model with the option to upscale x2.

Stable Diffusion 3.5 models do not work well for images below 600x600.






70
Game Editor Questions/Answers/Bugs / Re: Game Editor
Last post by Jeff -
Here is a list of the different objects so far that you can use in the game.

Objects breakdown (Object number determines type of object)

Objects number 1-29 = Wall objects (Objects 1-10 solid wall (Indestructible), Objects 11-20 destroyable wall, Object 21-29 Hidden item in wall)
Objects number 30 = Increase Player life by 1
Objects number 31 = Increase Player score by 50
Objects number 32 = Increase Player score by 100
Objects number 33 = Increase Player energy to 100%
Objects number 34-90 = Pickup item objects (Like Keys, Powerups)
Objects number 91-98 = Enemy objects (Objects trying to kill you)
Objects number 99 = Player object (You)
Objects number 100 = Special Enemy bullet object (Graphics to use for enemy bullet)
Objects number 101 = Special Player bullet object (Graphics to use for player bullet)
AI Image Central - Welcome to our forum!