Hello everyone,

This Checkpoint Merge aims for a more anime style.

I have used these settings almost exclusively. They are a good starting point and can be adjusted depending on what you want to generate.

Parameters for Pony

Sampling method:

• EULER A

• DPM++ 2M SDE

• DPM++ SDE

Sampling Steps:

• 30-40 Sampling Steps

• CFG Scale: 6-7 (Most of the times)

• clip skip 2

Example For Negative Prompt:

• ...

• ...

• ...

Recommended Upscaler Settings:

Hires. fix Upscaler:

• Hires steps: ~20

• Hires upscale: 1.5-2

• Denoising strength: ~ 0.3-0.5

Parameters for SD1.5

Sampling method:

• DPM++ 2M SDE

• DPM++ 2M Karras

Sampling Steps:

• 25-32 Sampling Steps

• CFG Scale: 3-5 (Most of the times)

Example For Negative Prompt:

• asian, bad hands, deformed, blurry, multiple arms, render, cartoon, cgi, render, illustration, painting, drawing

• asian, (deformed, distorted, disfigured), poorly drawn, bad ???????, wrong ???????, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, render, cartoon, cgi, render, illustration, painting, drawing

Recommended Upscaler Settings:

Hires. fix Upscaler:

• 4x-UniScale-Balanced [72000g]

• 4x_NMKD-Siax_200k

• Hires steps: 10-20

• Hires upscale: 1.5-2

• Denoising strength: ~ 0.2-0.4

If you can use Hires.fix for better Results!

I don't use restore faces. use ADetailer for a better face!

If you like this model, I would greatly appreciate a positive review along with constructive criticism, suggestions for improvement, or anything similar!

Recommended Settings:

• Sampling method: DPM++ 2M Karras, DPM++ SDE Karras... are my favorites

• Sampling Steps: 25

• clip skip 2

Upscaler Settings:

• Hires. fix Upscaler: 4x_foolhardy_Remacri, R-ESRGAN 4x+ Anime6B, 4x-UltraSharp, 4x_fatal_Anime_500000_G... are good

• Hires steps: ~ 10

• Denoising strength: ~ 0.3-0.5

If you can use Hires.fix for better Results!

I don't use restore faces. use ADetailer for a better face!

I would greatly appreciate any feedback!

If you like this model, I would greatly appreciate a positive review along with constructive criticism, suggestions for improvement, or anything similar!