The artistic style has been ft base the Pony XL model, following the guidelines of the Animagine XL V3 caption rules, by training with the collective works of 55 artists. A detailed inventory is included, although not every term may yield effective results.

Sorry, a mistake yesterday,in the final step I merge 5 layers from js2pony. I tested it and the difference isn't significant, so I don't feel like re-uploading.

Let's just go with the flow (●'◡'●).

please add artist name in the list to prompts if you want to get some style.

use prompts like use pony XL

artist list in dataset(sort by random?):

1. hoji (hooooooooji1029)

2. fuzichoco

3. kani biimu

4. kfr

5. mika pikazo

6. scottie (phantom2)

7. toosaka asagi

8. atdan

9. dsmile

10. gin00

11. happoubi jin

12. hiten (hitenkei)

13. kazutake hazano

14. ke-ta

15. kedama milk

16. mignon

17. misaka 12003-gou

18. momoko (momopoco)

19. morikura en

20. noco (adamas)

21. shiratama (shiratamaco)

22. torino aqua

23. amashiro natsuki

24. anmi

25. as109

26. ask (askzy)

27. fangxiang cuoluan

28. kaede (yumesaki kaede)

29. matanonki

30. mochizuki kei

31. rin yuu

32. soraneko hino

33. tiv

34. toraishi 666

35. toridamono

36. ciloranko

37. ogipote

38. poco (asahi age)

39. jima

40. miv4t

41. noyu (noyu23386566)

42. quan (kurisu tina)

43. rurudo

44. sy4

45. hito komoru

46. snow is

47. weri

48. akakura

49. binggong asylum

50. chen bin

51. nekojira

52. akizero1510

53. hong bai

54. da mao banlangen

quality_tag_list(in this ft caption):

1. "masterpiece",

2. "best quality",

3. "great quality",

4. "good quality",

5. "normal quality",

6. "low quality",

7. "worst quality"

year_tag_lsit(in this ft caption):

2005 <= year <= 2010: year_tag = "old"

elif year <= 2014: year_tag = "early"

elif year <= 2017:year_tag = "mid"

elif year <= 2020: year_tag = "recent"

elif year <= 2024:year_tag = "newest"

dataset from:

https://huggingface.co/datasets/KBlueLeaf/danbooru2023-webp-2Mpixel

https://huggingface.co/datasets/NebulaeWis/gelbooru_images

images process and filter : https://github.com/deepghs/waifuc/

caption & creation dataset : https://github.com/KohakuBlueleaf/HakuBooru

other code :me

License

This model is released under Fair-AI-Public-License-1.0-SD
Plz check this website for more information:
Freedom of Development (freedevproject.org)

描述:

训练词语: