Wan (<a target="_blank" rel="ugc" href="http://hucwos.com">hucows.com</a> version): This model was trained on 20 videos from <a target="_blank" rel="ugc" href="http://hucows.com">hucows.com</a> as a test to see how well it can learn the motions from the videos. High chance for logos as i was not willing to erase the logo fom 6000 images. Flux v2 and Wan v1: Same dataset as Wan version. Difference to old version, its trained on more variete of data instead of 90% realisitc its now about 50% realistic, 25/ cartoon/anime and 25% 3d cgi. therefore this version is not as restricted to stationary restriction and can place milking machines much more freely while still being able to maintain the old look. also its retrained to capture more data. SDXL/PONY/FLUX V1: These models were trained on a collection of 150 images and work well for realistic as well for 2d images.

Hucow Milking

Now the cleaned up dataset for pony too.

milking_v3_pony.safetensors

v3.0 Pony

v1.0 K2

v1.0 Ideogram4

v1.0 ZIT

v1.0 Wan (Hucows.com)

v2.0 Flux

v1.0 Wan2.1

v1.0 Flux (v3 dataset)

v3.0 SDXL

v2 SDXL

v2 Pony

v1 Pony

Files with SHA256: 6547bed338c6f712a8d7835e93db719f7b56c282c60f56272911de7e62e7aada