Photo Anima

Further improved Anima 1.0 version trained on a smaller but more photorealistic dataset at a higher resolution and for more steps. I found this version to be overall more realistic and detailed than prior ones, especially with the correct sampler settings and negatives. The trigger word is still "ph0t0an1ma", but I have found that "photograph" helps improves the realism, and if you are doing a specific character, use "cosplayer" after the character name to ensure realism. The ideal settings I have found to be are around 30 steps, a CFG of around 5, and most importantly, the DDIM sampler, as base euler and DPM samplers will produce more 3d CG results rather than photo-like ones.