Comments

[hidden]

kaisu1 said:

Hi what model formula did you use? Looks good!

Animefull(t2i) -> AbyssOrangeMix2_hard(i2i)

---t2i parameters---
Steps: 28, Sampler: Euler a, CFG scale: 11, Seed: 1636018072, Size: 768x576, Model hash: 925997e9

---i2i parameters---
Steps: 28, Sampler: Euler a, CFG scale: 6, Seed: 909055350, Size: 768x576, Model hash: 931f9552, Denoising strength: 0.7

Updated by Muffalo

[hidden]

interesting part is that this picture is pretty because i set up stable diffusion wrong.

desaturation was partially caused by "auto" in VAE settings. After I set it to nai.vae, it became more saturated (still good tho: https://files.catbox.moe/850cnu.png ). You can try disabling VAE (set to "auto" or "none" in settings) for more desaturation.

Read here for more info: https://rentry.org/hdgrecipes#bruising-in-merged-model-outputs

Updated by perelem

Show 4 more comments
[hidden]

avrix said:

Thanks. Yeah, I tried same prompt, same model mix, same seed, I found I wasn't even able to get close to a similar anime style output.

Can you give me the hash of the models you used? My result hash is different, might be slightly different models

[hidden]

@antlers_anon are you sure there's no hypernetwork you've selected in your settings tab, or TI that's being used to generate this image?

I tried to generate this with your provided mix__2.ckpt with all of the exact same settings (prompt, sampler, CFG scale, seed) and it still results in a fairly realistic non-anime style.

If nothing else, would you be willing to share your embeddings folder and hypernetworks folder? (just a screenshot would probably do as well?)

edit: looks like the firstpass width/height was set to 0x0, so it was just straight-up going for 768x1280 for initial resolution. I ended up finding that it gets pretty close, especially if I use kl-f8-anime2.vae instead of novelai/anythingv3 vae.

I'm guessing that colour correction and some filtering adds a little noise

Updated by avrix