Pony Vision!
This model was trained using a dataset of nearly 400 anime images. The training process involved approximately 30k steps.
Interestingly, I realized after the training that I had inadvertently used my old SDXL dataset. However, this didn’t seem to affect the quality of the output images, which turned out to be quite impressive. I hope you all like it and I look forward to your feedback in the comments.
Tips :
Positive Prompts: Using prompts such as (score_9, score_8_up, score_7_up) tends to yield excellent results. I’ve tried without these prompts and still got good results, possibly due to the quality of my training dataset. But as long as everything works fine, who cares, right?
Negative Prompts: (score_4, score_3, score_2, score_1, bad hands, bad feet, missing fingers, missing arms, missing legs, 3D, photorealistic, hyper-realistic, realistic, rough sketch, fewer digits, extra digits, watermark, signature, text font, username, logo, words, letters, digits, autograph, trademark)
✅Recommended Parameters V1✅
VAE : Already baked in
Aspect Ratio : SDXL resolution
Sampling Method : Euler a➡DPM++ 2M Karras | Both samplers work fine
Sampling Steps : 20➡30
CFG Scale : 5➡10
Clip Skip : 2
Upscaler : 4x-UltraSharp➡ESRGAN_4x➡4x_NMKD-Siax_200k
Hires Steps : 10➡20
Denoising Strength : 0.3➡0.5
Join my community, Share your feedback, learn, and have fun with us! 😊
Discord➡️https://discord.gg/QQKd7bu97P
User Guide 📢
I'm here to help you create awesome visuals! Remember, I can't be responsible if your content breaks any laws or community guidelines ❌
Let's collaborate creatively, follow the rules, and make something amazing together 🎨
📜 If you have questions, feel free to ask anytime! 🌟
