Tensor.Art
Create

AniPony XL

CHECKPOINT
Original


Updated:

3.5K

Recommended Settings:

Sampler: DPM++ SDE

Sampling Steps: 20 - 50

CFG Scale: 5 - 9 (depend on the prompt. If it long prompt choose between 8 - 9. If short prompt choose between 5 - 7)

Positive prompt: score_9, score_8_up, score_7_up, masterpiece, best quality, absurdres, very aesthetic

Negative prompt: score_6, score_5, score_4, monochrome, desaturated, loli, child, worst quality, low quality, lowres

This is the next version of my AnyponiXL V2. The reason I separated this version 2.1 is that it didn't reach my expectations. The quality is better, but the accuracy of prompts is slightly worse and less versatile than before. However, I like this model because it creates a nice 2.5D art style. So this is more of a variation of AniPonyXL - v2 rather than an improvement.

Comparison between V2 and V2.1

AniponyXL V2:

  • Higher prompt accuracy

  • More versatile

  • Possibly better at fingers than V2.1 (uncertain)

  • Slightly lower quality than V2.1

AniponyXL V2.1:

  • Lower prompt accuracy

  • Less versatile

  • More oriented towards 2.5D style

  • Hit-or-miss on fingers

  • Better overall quality

Version Detail

Pony

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.