My ignore list is growing …

There are NO working video generators on perchance. Perchance does NOT provide video generation services. You can NOT create videos using perchance.

You can ONLY generate images from prompts, nothing else - and chat with the AI.

Any generator claiming otherwise is wishful thinking, fake or worse (there are very few ones that “borrow” resources from outside of perchance and make it seem like perchance can do, which adds to the confusion.)

In your case, you can take a look at the code (edit button top right corner) and see this piece of “code”.

I tested your link with a character that can “read” websites to see how big the text actually is. The highlighted part basically says “This is way too much text, I’ll ignore what is over the maximum I can handle.” Since all of perchance uses the same model for AI text things, a generator with the sole purpose of creating lore out of something like that will face the same problem - you’d need to use a major company LLM for that with a higher token limit.

This is ALL of the text on this site (~21,600 characters), just the synopsis text would be fine, that’s not even 7,000 characters.

I fed that synopsis to Loreena, a character created by Petra to create Lore entries, this is the result:

Maybe this is close enough to what you are seeking. If not, you can try the same with Gemini or other major company LLM for probably better results.

Styles are just words added to your prompt automatically. You can use a major AI like Gemini with IMG2TXT capabilities to get a description of the art style - they usually refuse NSFW ones though. You could use https://huggingface.co/spaces/fancyfeast/joy-caption-beta-one for that. Maybe the results will be close enough this way

That was correct for the previous Stable Diffusion model, but no longer applies to the current customized Flux.1-schnell

The generator doesn’t know Charlotte or Kristin, there is no information about the location or anything at all. You’re just putting two vaguely different piles of keywords into a void, leaving the gaps for the generator to fill in.

Here are two quick & dirty examples of how you could do it (graciously provided by an AI prompt enhancer helper character). You don’t have to do it exactly like this, you can use art styles etc. the generator you are using provides, you can leave out details for the generator to fill in, but you should give a clear idea of how things/persons interact with each other so it actually “knows” what you want. Notice how Charlotte is always on the left and always looks like her description? And how there’s always the bench and the fountain, the park, leaves etc.?

Charlotte, a slim woman in a practical grey jumpsuit, leans casually against a wooden park bench on the left side of the frame. Her long blue hair spills over one shoulder as she laughs with genuine amusement, eyes crinkling at the corners while pointing playfully toward Kristin. Sunlight streams through golden autumn leaves, illuminating dust motes dancing in the air around her. Kristin stands near a mossy stone fountain on the right, fiddling with the hem of her green dress as she stares at rippling water. Her short blonde hair catches the afternoon glow, cheeks flushed pink beneath freckles visible in the natural light.

• Art style: Casual candid photograph with shallow depth of field and natural color grading.
• Composition: Charlotte occupies left third with bench and oak tree trunk. Kristin positioned right-center near fountain edge. Background features blurred park visitors walking dogs along distant path.
• Lighting: Soft directional sunlight creating gentle highlights on hair and skin textures.
• Color palette: Warm amber tones dominating foliage, contrasting cool grey jumpsuit and vibrant emerald dress.
• Details: Slightly out-of-focus maple leaves foreground, water droplets frozen mid-splash in fountain, scuff marks on Kristin’s ballet flats.
• Technical: 85mm lens, f/1.8 aperture, ISO 200, 1/500s shutter speed capturing motion in fountain spray.
  

Charlotte, a slim woman in a grey jumpsuit with cascading blue hair, leans against an ornate park bench on the left side of the frame. She laughs openly, one hand covering her mouth while the other gestures mockingly toward Kristin. Sunlight filters through autumn oak leaves, casting dappled shadows on her smug expression. Kristin stands near a fountain on the right, her green dress rumpled as she stares at her own reflection in the water. Her short blonde hair catches the golden hour light, cheeks flushed pink as she nervously twists a fallen maple leaf between her fingers.

• Art style: Watercolor illustration with soft edges and warm natural tones, evoking storybook aesthetics.
• Composition: Charlotte occupies the left foreground with bench and flowerbed. Kristin positioned right-middle ground near stone fountain. Background features winding gravel path, distant bridge, and foliage in fiery oranges/reds.
• Lighting: Late afternoon sun creating long shadows, backlighting Charlotte’s hair with halo effect.
• Color palette: Earthy russets and ochres dominate, contrasting Charlotte’s cool jumpsuit and Kristin’s vibrant dress.
• Details: Crumbled leaves near Kristin’s shoes, intricate ironwork on bench, water droplets catching light in fountain spray.
• Technical: Medium telephoto compression, subtle bokeh on background trees.
  —

Feel free to hop over to #text-to-image on https://discord.gg/4fPDXBzYwV and take a look at the images posted there. If those are reduced quality, then I can’t imagine what images will be once it’s back to normal …

Hm … maybe if you paste some of your images, we can recreate that style?

Keeping Perchance free comes at a price. In this case, the price is limited options for both chat and image generation (speed, one single model, and for images no inpainting, no IMG2IMG or IMG2TXT, fixed resolution …)

Perchance only offers Text to Image, but there’s at least one generator that “borrows” resources from a few other sites, click on the top left icon (three bars)

Perchance does NOT support video generation, only chat and image generation from text. Any generator claiming otherwise is a fake, wishful thinking, prank, or possibly malicious.

As a non-floridian, that law is of no interest to me. Same as the Penal Code of Japan, else all NSFW images would need to have those funny “decency bars” or be illegal.

Start a new chat with your version of Chloe or manually remove the python window by editing her comments for a while. The AI “remembers” the last 20 or so replies and uses those as base for new comments. If you have enabled summary and memory, this might be somewhat fruitless without even more editing of those.

Older custom generators that have not been updated since the change from Stable Diffusion to Flux still are “stuck” with those resolutions. Anything else got the improved 768x768 resolution. If you still want to use one of those, try adding (resolution:::768x768) to your prompt.