AJDragon

joined 6 months ago
 

Hi

I was just wondering if anyone has ever done a short story with ai-character-chat and let the AI narrator create a Rod Sterling twilight zone ending monologue for the story? I just did this and got a laugh out of how well of a job it did.

 

Has the format changed for the ai-character-chat, i have noticed that the ai seems to be spitting out a paragraph or two of unnecessary content. For instance if I say Hi to the chat bot it will reply with a paragraph or two of unnecessary content before replying with a Hello. I can minimize the unnecessary content by changing the response length to one paragraph. It used to be I would get the response first and then a lot of unnecessary chatter content which you could eliminate by shortening the response length.

[–] AJDragon@lemmy.world 0 points 1 month ago

Hi, I have noticed some of those myself, One ai chat bot I made had pet mouse and the ai named it Marrow, and when I added a extra npc to a chat story the ai named it Juno.

 

Hi I tried making a perchance text to image persona/chat and for some reason perchance.org/ai-character-chat says "error during load. Try reloading page." And also "It seems you've tried to load a character share URL, but the file specified by the URL does not exist. If you believe it should exist, you can ask for help on the community forum, or check if the file has been quarantined:" Could it be because it contains two personas?

[–] AJDragon@lemmy.world 1 points 6 months ago* (last edited 6 months ago)

Hi

Here is a video you might find helpful. https://www.youtube.com/watch?v=7h87NOrkc1M

[–] AJDragon@lemmy.world 1 points 6 months ago (1 children)

Hi

You have probably figured this out already, but if you haven't then you can try this. Please understand that this is how I make my prompts and they seem to work halfway decently. I also use an external note pad program, namely "word pad, Rich Text Document" to wright all of my prompts in first. I do this namely because you can not use the enter key to move to the next line of dialect. Spacing is very important when creating your prompts.

Try using the words, "Two People. or Three People. or Four People.". These have to be the first words you wright if you are adding multiple people. Then double space, and then start describing the first person, start with what there body looks like, " when I say body I mean the whole body from head to toe" then there clothing, add coma's, apostrophes, quotes, and spaces, but do not use a period until you have finished the first person. You will end up with a long continues sentence, describing the first person. Also make sure the spacing between words is done right, two spaces between two words is enough to derail your description.

Here is a "VERY" simple example.

The extra spacing between descriptions makes a big difference, I us double row spacing.

[–] AJDragon@lemmy.world 1 points 6 months ago

Another question , is there a way to use image prompts with Perchance?

[–] AJDragon@lemmy.world 1 points 6 months ago* (last edited 6 months ago)

Hi

Using just this prompt "sprung, solo vintage police motorcycle, "two tone red and white livery seat". " and a snap shot from the video of the seat I was able to get this within 10 tries.

This is the snapshot I used With some tweaking to the prompt and a better image you should be able to recreate what you looking for.

[–] AJDragon@lemmy.world 1 points 6 months ago (2 children)

Hi Have you tried other free AI text to image generators? Before switching to Perchance I used https://freegen.app/, it has limits on what it is allowed to do "like not showing naughty stuff" but it does seem to do a good job of recreating none human based items and things. You might want to give it a try if you haven't already. One thing I like about it is you can add "1" image prompt, so you might be able to in corporate the seat that way by having a picture reference.

1
submitted 6 months ago* (last edited 6 months ago) by AJDragon@lemmy.world to c/casual_perchance@lemmy.world
 

Hi

First and foremost I suck at spelling and rely on spell correct for non base words or big words. Writing anything beyond a basic sentence is a little difficult for me.

I am new to Perchance AI Text to Image Generator, I can make a basic prompt, but it's the little things that should be added to prompts to make them work right that I am missing.

Question 1: Quotes " " and other symbols in prompts, when should they be used in a prompt?

Questions 2: How do you move to the next line of text, the Enter key is directly linked to the Generate Image button. Or are you just supposed to use a long train of sentences, to describe everything?

Question 3: What other non word things can be add to a prompt, like adding :1.5 after a item or frays will increase it's likely hood of being in the image. For instance "a blue baseball hat:1.5", .

Question 4: How do you repeat the same item or character to use in multiple images as in a comic strip.

Question 5: How do you make bigger sized, higher resolution images, the ones generated seem to be a little on the small size.

At the moment this is all I can think of, but there will be more.

[–] AJDragon@lemmy.world 1 points 6 months ago (5 children)

Hi

That unpredictability factor is what is really screwing with me also, I like repeatable results, and the ability to tweak the item but that does not seam to be a feature of the Free AI Image Generators, or at least I just have not figured out how to yet.

The only other thing I can think of is prompt picture referencing, and I don't know if the Perchance Free text to AI Image Generator has this ability. a lot of the non free AI Image Generators have that ability.

Just out of curiosity , what kind of Image are you trying to create?

[–] AJDragon@lemmy.world 1 points 6 months ago (7 children)

Hi, I am new to AI but I use google to find the actual names of the things I want the AI to generate, in you case try incorporating "sprung, solo vintage police motorcycle seat" into your prompt. that is what type of seat that is.