V8 is a mix of the past v7 v6 and v5.
V8 mix B has better knowledge of characters and need less weighting to get colored skin for example. Not that it is always correct but it has a better idea of who a character is.
Either way both can be interesting, curious which one you prefer.
Rule of thumb for both hyper versions, if you get artifacts either our cfg is too high or your steps too low. Hyper versions are Euler and Euler a only most other samplers don't really work.
Version 6 seems to behave with most samplers, not sure if I would recommend Euler a however.
Removed 5.1 it was too buggy so I removed it.
Not sure if Clip merging is such a good idea especially with Pony models.
Did remove the T5 clip merge as it looks like it does not work, or only has an effect with A1111. If you are using Comfy UI there is no difference between v4 with or without T5.
The real version 9 of my fast Pony merge.
I decided to publish this under a new name as it will where I try to get the look I want (more then in the other one where I tried to keep everything Pony intact).
I don't think I broke anything Pony like yet...
Will leave the name however as "fast" as it is based on version 7.5 and you can get decent results with 10-12 steps.
Don't use Euler a, especially with version 2 (at least for me it causes issues)
DPM ++ samplers are fine
I hope nobody minds the prompts I have been borrowing to se how mine compares.
Description
Changed quite a bit so it is version 2 instead of 1.1 (some prompts look very different too).
Should fix the somewhat wonky faces version 1 (probably).
We do not talk about hands ;)
FAQ
Comments (5)
The amount of details this thing produces is mind boggling. Sadly it's not as easy to get good images to work on as 7.5 was but good damn the visual quality is incredible. The amount of fuzz hair i see and the depth of field effects *chefs kiss*
Thanks and I agree not sure how to fix some things yet.
I might try to somehow mix my 7.5 in and see what happens, perhaps with some v9 or the unreleased 1.1 of this.
Also it has a bit of an white dot issue perhaps I have to check my Lora training data or so.
@TiwazM btw i cant agree with your Euler a warning. Infact i have the feeling it gives far better face details but worse vibrant colors compared to the sde samplers. But i usually do a face inpaint after upscaling anyway so its not a big deal overall. As always great work with the checkpoint.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.