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

Merge of 3 of the best Pony based models:

First merge was 0.5 Comrade into Autism confetti, and then 0.33 T-ponynai into that one.

Good with anime. (Missing original Pony Pony Diffusion V6 XL ability to have pony, furry and cartoon styles)

Recommended VAE is sdxl_vae. VAE is optional, but sometimes it produces a better result with it but not always.

The base of all is Pony V6, which had the issue with the scores, so adding the complete "score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, " at the strat of the prompt does help with the quality.

Recommended settings are:

  • Sampling method: Euler A

  • Sampling steps: 30

  • Width and Height: 832 x 1216

  • CFG Scale: 7

Personal extra recommendations:

  • Use Hires Fix. with 15 steps, 0.4 denoise and 4x-UltraSharp upscaler

  • Use ADetailer with face_yolov8n and mediapipe_face_mesh_eyes_only

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

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