VanillaFlower

joined 3 months ago
sorted by: new top controversial old
[Suggestion] Be able to use LoRAs, LyCORIS, Embeddings, VAEs, and other types of models, and select a checkpoint (for Text to Image Plugin) in c/perchance
[–] VanillaFlower 1 points 2 weeks ago* (last edited 2 weeks ago)

@[email protected]

How to generate amputees without prosthetics or random objects attached to the tip of the stump? (question related to AI Text to Image Plugin) in c/casual_perchance
[–] VanillaFlower 2 points 3 weeks ago* (last edited 3 weeks ago)

I don't think the prompt "Grab a machete" would generate amputees with no prosthetics. It just generates someone holding a machete. /nm

1
How to generate amputees without prosthetics or random objects attached to the tip of the stump? (question related to AI Text to Image Plugin) (static.wikia.nocookie.net)
submitted 3 weeks ago* (last edited 3 weeks ago) by VanillaFlower to c/casual_perchance
3 comments fedilink
 

I know how to generate amputees (you have to put "amputee" in the prompt to generate it). But I wanted to generate amputees, with no prosthetics or random objects attached to it (like the image of Handy from HTF shown).

There are generated images depicting an amputee with no prosthetics or random objects attached to the stump, but I wanted a prompt idea to make AI generate images of amputees with no prosthetics or random objects attached to their stumps (since just prompting "amputee" often makes AI depict prosthetics). I put "prosthetic" in the negative prompt, but that still wouldn't work, even with emphasis.

Any prompt ideas? Thank you.

Edit: I just got how to generate it. You have to put "(prosthetic:1.5)" in negative prompt.

How to generate Wubbox from My Singing Monsters? in c/casual_perchance
[–] VanillaFlower 2 points 3 weeks ago* (last edited 3 weeks ago)

I was able to generate what partially looks to be Sox from My Singing Monsters, with prompting. /nm

Comparing AI generated images to Sox

The closest one is the image with donuts (the image with donuts is shown above). The image of donuts depict a partially accurate fur color, an accurate eye color, green crystals on head, and green claws, something Sox's design has.

Images were generated with AI Furry Generator, and are posted to the 'sox' gallery.

3
How to generate Wubbox from My Singing Monsters? (lemmy.world)
 

I want to generate my favorite My Singing Monsters character, Wubbox (the one shown in the image), but I can't generate the character. I tried prompts like "upper part of head missing" and "limbs made of electricity" and emphasis, but they also don't help to generate the character. The closest prompt I could think of is "(wubbox, ambiguous gender, humanoid, robot, yellow body, red eyes, blue orb on torso, hole on torso electricity, lighting, blue electricity, limbs made of electricity, detached limbs, gauntlets, gray hands:1.25)", but it still doesn't help generate the character extremely accurately/exactly (the colors are accurate though). Any prompts for generating Wubbox from My Singing Monsters? Thanks.

I can't make my generator "public" in c/perchance
[–] VanillaFlower 2 points 3 weeks ago

Not a staff member of this community, but are you asking for help, or are you reporting a bug?

If you are just asking for help, click "edit", click "settings", then click "make public". Making a generator public is not too hard/difficult.

4
[Suggestion] Be able to use LoRAs, LyCORIS, Embeddings, VAEs, and other types of models, and select a checkpoint (for Text to Image Plugin) (self.perchance)
submitted 1 month ago by VanillaFlower to c/perchance
3 comments fedilink
 

Hello, Perchance Dev,

I have 2 suggestions for Text to Image Plugin (like in Civitai):

  • LoRA, LyCORIS, Embeddings, VAEs, and other types of models.
  • Be able to choose a checkpoint you want to use (of any base model).

I want to be able to use LoRAs, LyCORIS, Embeddings, VAEs, and other types of models besides Checkpoints. For example, if you're disappointed that AI didn't generate a character you wanted it to generate, you could use a LoRA or LyCORIS, and if AI generates images with boring dull colors, you could use a certain VAE to make colors look more vibrant.

I also want to be able to choose a checkpoint I want to use. For example, if I want to generate a cartoon anime image with vibrant colors, I might want to use Mistoon_Anime.

The way to use models/certain source of models you can use in Perchance is up to the developer's choice. Ability to import models from other sources (like in Tensor.Art) is also optional to the developer.