Watch it with source quality! Pls comment if you have a request video to postprocess with AI. Original creator is : 世纪末孤独的旅行家 (世紀末の孤独な旅人) https://youtu.be/e_zGcT-w5x8 [My comment on this video] AI postprocessing goal is to obtain anime-style from 3D-texture with consistency. It goes without saying that AI-ed face is better. 服はどうだろう. パラメータを調節してもう少しアニメ調に寄せることはできるとは思う。裸はAI-edの方が良く見える。 The params for img2img is below. Maybe Softedge(softedge_hed, weight 0.5, steps 0 to 1) with denosing strenght 0.6 to 0.7 can get better result, not softedge + tile. 1girlだけだと乳首の部分が上手く描写できていなかったので裸になるところからはnude, nipplesを加えてimg2img batchを再開しました。 params: 1girl, Negative prompt: (low quality, worst quality: 1.6), Steps: 30, Sampler: Euler a, CFG scale: 11, Seed: 345873655, Size: 720x1280, Model hash: 54ef3e3610, Model: meinamix_meinaV11, Denoising strength: 1, Clip skip: 2, ControlNet 0: "preprocessor: none, model: control_v11f1e_sd15_tile [a371b31b], weight: 1, starting/ending: (0, 0.5), resize mode: Crop and Resize, pixel perfect: True, control mode: Balanced, preprocessor params: (-1, 1, -1)", ControlNet 2: "preprocessor: softedge_hed, model: control_v11p_sd15_softedge [a8575a2a], weight: 0.5, starting/ending: (0, 1), resize mode: Crop and Resize, pixel perfect: True, control mode: Balanced, preprocessor params: (512, -1, -1)", ADetailer model: face_yolov8n.pt, ADetailer prompt: 1girl, ADetailer negative prompt: "(low quality, worst quality: 1.6)", ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.15, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.8.0, Noise multiplier: 0, Version: v1.5.1 [Info] my yt channel: https://www.youtube.com/@suzuR420 uploading AI generated videos and brief tutorial etc... not limited to MMD though. I'll upload a video about MMD postprocessing with stable diffusion later too.