Mimic styling of artist "1888" or "1.123"For Anima, trained locally withing ComfyUI using <a target="_blank" rel="ugc" href="https://civarchive.com/articles/29356/training-anima-in-comfyui">https://civarchive.com/articles/29356/training-anima-in-comfyui</a>The model is surprisingly weight responsive (in a good way) !with 0.8 you'll get the styling with sharp line bold lines, and you'll get the whole characters vibe at 1.0 !For the illustrious model:Trained locally using "VETE" base training checkpointThe artist like to mix sexy moment with mundane scene of violence and destruction.About V1A dataset and training:<ul><li>Has low amount of violence and destruction, but can still make proper explosion and concrets shards.</li><li>Balanced amount of characters, it can draw male and female properly.</li><li>Many characters (witches) are in, but not properly tagged yet.</li><li>Work fine with popular ill models (wai v15 v16, plantmilk walnut, VETE base lora training chktp)</li><li>For some reason use only low weight (0.6 or 0.7) if you using hassakuXL illustrious v34 otherwise the picture will be bad :( .</li><li>Some vehicle are in, but don't expect anything good.</li></ul>good effect start at 0.8.Enjoy :)Some pics at perfectly SFW but civit analyse tools is acting like a bitch ...

1888 | 1.123  style

Lora trained in about 2048 steps with comfyui anima trainerSame dataset as previously

Files with SHA256: 15586a52fd8cf576df5edc095eeec688d54a4b513ae79a37bdc9fc6487b488bf