Most likely SUPER not a priority. But you know me 😅

https://perchance.org/prompt-style-tester#edit

The “go” button updates the entire page. As the options are generated this means they are re-generated, which means the chosen option resets, and you can only ever test the top option: Painted Anime.

Simple fix though: put a div with an id around the generations, then update that div only. That’s all that needs updating anyway.

      • RedWolfEchoes@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        9 days ago

        Well again thank you so much, I’ve been trying to figure out a way to do this for so long, being able to chat with a custom character have them automatically generate images with somewhat accurate depictions of what’s happening in chat. Having a little trouble getting any NSFW images at least good ones, but that definitely could be on my end 😂. My next step from here is to add a voice emulator or text to speech that doesn’t suck and that everyone can use somewhat easily 🤣, been kind of looking at Suno bark but I’m not extremely familiar on how it works nor am I familiar with how I would go about coding it into the chat. @VioneT@lemmy.world

      • RedWolfEchoes@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        8 days ago

        So I hate to ask, but is there no nsfw allowed for the image generation, just curious because earlier today I came across a few scenes in rpg chat where nsfw was definitely depicted and it’s like the image generator went out of its way to show any content like that. Just wondering if it could be because of the custom jv code?

        • VioneT@lemmy.worldM
          link
          fedilink
          English
          arrow-up
          2
          ·
          8 days ago

          Not sure, I don’t really dabble on the NSFW content, so I won’t know lmao.

            • VioneT@lemmy.worldM
              link
              fedilink
              English
              arrow-up
              2
              ·
              edit-2
              3 days ago

              Can you send me the character link again. I would assume that you do not have [input.description] on the prompt or [input.negative] on negative on the pasted style like so:

                ...
                "Professional Photo": {
                  // When adding a new prompt, you need to add [input.description] to help the code know what would be the prefix and suffix of the prompt. [input.negative] is not as required.
                  prompt:
                    "[input.description], {sharp|soft} focus, depth of field, 8k photo, HDR, professional lighting, taken with Canon EOS R5, 75mm lens",
                  negative:
                    "[input.negative], worst quality, bad lighting, cropped, blurry, low-quality, deformed, text, poorly drawn, bad art, bad angle, boring, low-resolution, worst quality, bad composition, terrible lighting, bad anatomy",
                },
                ...
              
              
                • VioneT@lemmy.worldM
                  link
                  fedilink
                  English
                  arrow-up
                  2
                  ·
                  3 days ago

                  I tested it, and it seemed to be working properly, possibly something on the AI’s response inside the <image> tag that borked the code?

                  • RedWolfEchoes@lemmy.world
                    link
                    fedilink
                    English
                    arrow-up
                    1
                    ·
                    22 hours ago

                    Yeah maybe, because I have copied and pasted other styles into the code and some work and then there’s some that just don’t like when I go to change the style in chat that loads with a character responding to the command but not showing me the styles, or it’ll show me the styles but when I click the new one I added it won’t switch over. Hello is a style I recently added from another generator and for whatever reason it is not working, am I missing something?

                    “🎮 Danganronpa AnimePlus”: { “prompt”: "[input.description], (A (Danganronpa Art Style:0.975), (–anime:0.025), Illustration, Line Art, dynamic lighting, highly detailed, fine details, well-structured, unique character design, anatomically correct, proper proportions, Colors: vibrant and balanced). “negative”: "[input.negative], (low quality, worst quality, (excessively_pale_or_dark_skin_tones), (poorly_proportioned_philtrum), (animalistic_facial_structures), (elongated_snouts), (pointed_noses), (overly_pronounced_cheekbones_resembling_non-human_mammals), (inaccurate_facial_expressions), (elongated_pointed_ears), exaggarated features, inaccurate likeness, unrecognizable features, unrealistic resemblances, distorted facial characteristics, unattractive facial features, poorly structured teeth, rabbit-like teeth, feminine features on male characters, masculine features on female characters, ambiguous gender traits, incorrect proportions, error, cropped, blurry, blurred, deformed, malformed, disfigured, poorly drawn, incorrect positioning, awkward positioning, awkward pose, inappropriate distancing, mismatched body language, incorrect interaction, unnatural intimacy, poorly framed, animal, animal ears, exaggarated cock size, piercing eyes, two-tone hair, dual color hair, extra limbs, extra fingers, broken fingers, long neck, twisted body, bent body, distorted body shape, oversized boobs, oversized cock, fused fingers, mutated, mutated hands, malformed eyes, missing iris sclera, distorted face, distorted eyes, distorted hands, wrong anatomy, bad anatomy, incorrect hand anatomy, poorly structured, poorly drawn eyes, poorly drawn background, poor body language, unnatural hair, unnatural eyes, unnatural skin, excessive hair, out of frame, overposed, elongated, elongated body, elongated fingers, crossed legs, pixel, pixelated, text, watermark, title, signature, grainy, lack of emotions, lifeless, lack of details, lack of depths, jpeg, jpeg artifacts, drab lighting, overused, boring, predictable, clone, duplicate, out of focus), },