WaiSnackMix: Ongoing Efforts

Every few days or so I have attempted to improve it, using the same testing methods that went into version 1.0. I felt that if 1.0 was well received, then surely there are creators who would be eager to try the next version. However, this checkpoint's weaknesses have been rather elusive and its strengths rather easy to degrade, making modification tricky.

At long last, I came up with the idea to combine WSMv1.0 with Strange Thing Mix Anime by Zlax. The Wai style was fully preserved but it is slightly less toony, with less of a bias for large heads that seem to be leaning forward into the frame. Not that this was really a problem in the past, but it's a slight adjustment and I feel it's worthy of standing as its own checkpoint AND as an improvement over v1.0 so please feel free to try it, or switch to it. Overall they are still very very similar "twin" checkpoints.

What you get with WaiSnackMix

No baked LoRAs (unless they came in through the parent and predecessors models) and lots of stability, clothing options, and versatility. I have seen this model pull off amazing results in semi-realism considering that it was made to produce Wai anime style toons.

Speaking of Wai, some are curious about the name I used. This checkpoint had several inputs, making it hard to pin down a short and memorable name. So, I improvised. I will return to this point but first allow me to introduce the predecessor models of this checkpoint:

WaiNova 1.0 (base) by OGMustard - An awesome checkpoint for real, great adherence to begin with, go check it out. The color and style of this checkpoint shines, in a short time it has become recognized as a wonderful checkpoint to create and enjoy.

Strange Thing Mix Toon v2 (added) by Zlax - a softer look than WaiNova, one I really like, and with Zlax's care and testing regarding prompt adherence a known factor made it a top choice for me.

And again, no baked LoRAs.

Zlax and OGMustard make some of the best checkpoints around if their style matches yours. You absolutely should follow them, and you will find their models recommended below.

I was going to call it WaiStrangeNova but that’s just weird and pulls too much from Zlax’s brand. Mustard is a condiment and so Strange became Snack and merge became Mix. I couldn’t be happier with .

Since inception this checkpoint has earned enough buzz for me to keep it on site without coming out of pocket, so I thank you all for that. It also hit some download and like milestones which to me just kind of amazes me.

I recommend Euler A all around and some others below. Of course other combinations exist, and I have found this checkpoint can work well with Exponential approaches but they take longer. Heun tends to choke on complex situations and controlnets. Feel free to experiment.

Upscaling: Euler A and simple is my preference here, denoise of .3 or less in most cases.

Quality Tags Guide

Positive Prompt (slightly adds detail/refinement/shading quality, purely optional)

masterpiece, amazing quality, best quality, ultra-detailed,

For greater realism, fleshy lips, significant reduction in size of anime eyes:

masterpiece, realistic, amazing quality, best quality, ultra-detailed,

Replace with the following for a slight adjustment to toon style

toon style,

Other tags that affect generation, albeit slightly:

anime style, retro style, kawaii style

Tags that will profoundly alter the style, if used all together:

vibrant hues, dynamic pose, blue palette, realistic, abstract background,

As for prompts, it is very good at understanding booru format and lengthy natural language prompts. However, very brief and short prompts can, depending on the subject matter, confuse checkpoints. I highly recommend using the preview KSampler from efficiency nodes so that you can see what is happening during the layout phase of generation as it helps to demystify things.

Generation Settings

EulerA, Simple or Karras - works great

CFG 5

Steps: 25-35 DPM++SDE with Karras-

CFG 2-6 (yes, 2 is perfectly fine, maybe better, 1 is 40% faster and comprehends prompts but sepia tones creep in)

Steps: 25-35

CFG at 3 or higher tends to give that bright, anime look but shading can suffer, especially if you want a scene of evening romance in the bedroom.

You can also experiment with lightning generations, slightly lower quality but iteration rate increases by 200% and you need fewer, resulting in generations only taking 3-5 seconds:

Euler A / Simple

8 Steps

CFG ~1.5

I'm curious to hear what you have to say about these settings, if people insist on CFG 1, I don't see how those outputs are acceptable with this checkpoint, fast or not if it looks all faded and sepia it's a no-go.

The following settings work great, phenomenal, but do not combine with the SDXL lightning lora, don't even try.

exp_heun_2_x0_sde

exponential

20 steps

CFG 3

There are so many tags that it responds to, I can't possibly hope to begin, just grab your favorite tag reference and go for it.