AniMagic XL

Introduction

Originally I was going to create an XL Version of my aesthetic Mix. But as I was working on it the past week or so it morphed into an XL Version of AniMagic. Sorry, not sorry. It's pretty cool. Try it out. It doesn't do the more hardcore ???? acts as well as AniMagic 1.5 does, but it does have much better aesthetics, backgrounds, and it's an XL Model. The example images are similar prompts to those used for AniMagic 1.5 but not all of them identical especially when it comes to the ???? ones.

Disclaimer

All prompts in the example images use InvokeAI Syntax NOT Automatic1111 syntax. The key thing you need to know is that 'term+' is equivalent to '(term)' ++ is the same as (()) and so on. All example images were generated in InvokeAI with xformers enabled. InvokeAI also converts all safetensors or ckpt files into diffusers models before generating images. For these reasons you will likely not be able to reproduce my example images 1:1.

Prompting & Generation

Scheduler: Euler or Euler a

Steps: 20 - 50

CFG: 5 - 10

CLIP Skip: doesn't matter

Pretty much all of my prompts start like this. Then I fill in the blank with what I want to see and it works very well. But this model does a really good job of handling different lighting conditions, so try whatever you like. For descriptions of what you want, try using Booru tags, the CLIP in this model is based on a ?????? model so that will work best.

Positive Prompt: (masterpiece)+, (best quality)+, highres, high quality digital art of _____, high contrast, soft lighting, backlighting, bloom, light sparkles, chromatic aberration, smooth, sharp focus, (detailed)+, 4k, 8k uhd, (perfect ???????)+, sharp, (intricate detail)+, (detailed background)+

Negative Prompt: boring background, plain background, censored, (worst quality, low quality), greyscale, monocrome, multiple views, blurry, text, signature

Credits

Thank you to everyone out there who is working so hard at training models. Sometimes I feel like I just come along and try to capitalize on work that other people do without any real effort. Then I look at my merging notes, the days of time and effort that goes into each one of my merges. Notwithstanding though, I wouldn't be able to merge anything if these wonderful creators hadn't made all these excellent models.

• ?????? Mix XL Road to Freedom v4.0

• Hassaku XL Beta 1

• SDXXXL v 3.0

• Afrodite XL NSFW

• Pyros ???? SDXL

• Osorubeshi XL NSFW

• Deep Dark ?????? Mix NSFW

• Disney Princess ?????? Mix

• Duc Haiten Real 3D ???? XL v1.0

• Yamers Cartoon Arcadia v2

• Realistic Freedom Wonderland

• Matrix ?????? Plus XL

• Not Real Realistic SDXL

• One Mix XL v 3.0

• Only for ???? 118 v1.0

• Faetastic SDXL