Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

PLEASE READ - WORKFLOW BELOW:-

This will probably be the LAST UPDATE for the Dragonfruit models, for a while, at least until I am happy enough with my realistic merge (currently WIP), once it's complete, I will probably update Z.5D to v2, or if I discover any new ways or information on merging.

Please wait patiently for my next models, completely separate from the Dragonfruit branch!

DragonfruitGT v1 (Z v2) - More fantasy, more range in color, better landscapes and more masculine men.

  • Please use DragonfruitOG v2.0, if you prefer the thicker lines, less detail and simple color pallet.

If you have enjoyed this series of models, please leave a rating! Thanks as always!

__________________________________________________________________________________

GT v1.0 (Z v2.0):

  • Better backgrounds

  • Deeper contrast - more color

  • Bolder lines

  • MORE DETAIL

-Settings for GT:

-Steps: 30-50

-Clip skip: 2

-Upscaler: Euler a / DPM++ 2M SDE Karras

-Adetailer extension

-VAE: berrysmix

__________________________________________________________________________________

Workflow for my images -

  • Please use the BerryMix VAE ensure your image has correct color

  • Use Adetailer (After Detailer) extension to improve many things such as faces, bodies and hands. Other Adetailer models can also be found on Civitai and Huggingface:

  • Hires fix with denoising strength of 0.3 - 0.35, using upscaler "x_NMKD-Superscale-SP_178000_G":

  • Move the hires image to img2img, using a denoising strength of 0.3-0.35 and keeping the same prompt, negative prompt, settings (cfg, CLIP, steps, sampling), AND seed. Generate this image, (MAKE SURE TO USE THE NEW HEIGHT GIVEN AFTER HIRES), this will inject more color and detail into your image:

  • Next move this new Img2img generation back into Img2img once again keeping the same prompts, settings and seed, but with a LOW denoising strength 0.1-3.0 (sometimes at high denoising strength 2.0-3.5 it will create eyes and faces inside of your image). Use the SD upscale script with the "RealESRGAN_x4plus_anime_6B" sampler to increase your image size:

(Civitai lowered the quality so you cant't tell, image on left is 512x768, image on right is 4096 x 6144, 8x THE SIZE!)

__________________________________________________________________________________

Z.5D v1.0:

DragonfruitZ.5D v1:

  • 2.5D style model

  • Derived from dragonfruitZ and a realistic merge (work in progress)

  • Features skin color variety, masculine men, landscapes, fantasy, nsfw content, and detailed faces

Settings for Z.5:

Steps: 30

Clip skip: 2

Upscaler: Euler a

-Adetailer extension

-VAE: berrysmix

__________________________________________________________________________________

OG v2.0:

DragonfruitOG v2.0:

  • Refinement of the OG Dragonfruit model

  • Focus on bold, clean lines and bold colors

  • Decreased detail for simplicity

  • Improved teeth, skin color variety, and landscapes

  • More fantasy elements

  • Enhanced nsfw content

  • Exciting releases in the future

__________________________________________________________________________________

Z V1.0:

DragonfruitZ v1.0:

  • Dragonfruit Z - an alternative version with more fantasy and color range

  • Better landscapes and more masculine men

  • Use Dragonfruit (Unisex) v2 for thicker lines and simpler colors

__________________________________________________________________________________

OG v1.0:

Dragonfruit OG v1.0:

I enjoy 2d, flat, colorful, thick lined checkpoints, but I always struggled to create male characters, with the checkpoints I use. I've decided to create a merge that is a little bit more unisex. I REALLY enjoy using this, so I though I'd share it. (this is my 1st merge, please have patience.)

  • Introducing a merge that's more unisex

  • Suitable for creating male characters

  • Personal settings provided for reference

Settings I use:

Steps: 20-30

Clip skip: 2

Upscaler: Euler a / DPM++ 2M SDE Karras

-Adetailer extension

-VAE: berrysmix

Thank you for your continued support and feedback!

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.