Added some examples with "stolen" prompts from other models.<s>Euler Ancestral only</s><s> (all other look broken)</s> o1.1 is differentThis is a blocks merge among all official Anima models (from preview1 to Aesthetic 1.1). There are no training or LoRA usage.For realism use this (long prompts break realism, sadly - the model needs training to support it properly): Positive ("low quality" tag is not a mistake, but you can remove it):<pre><code>(realism, realistic, photography), low quality,</code></pre>Also add "cosplay" word for an anime character.Negative:<pre><code>(anime, animation, disney), (@3dcg:0.8), 
bad quality, simple background, mirrored, blur, AI generated,</code></pre>Anime style is default (I can do nothing with this without training).

Anima-o1

Just an experimental merge that shows good results in some areas. Not a big change in weights, but results may be different.

Files with SHA256: dfee1624fad05257fc18f37267887428477864e34a9c9877318009f2013de7e8