Three-dimensional　ink　rendering　is　a　NPR　(Non-Photorealistic　rendering)　art　style,　widely　used　in　a　range　of　fields,　including　gaming　and　animation.Although,　CycleGAN　is　a　standard　image　transformation　model,　however,　it　prefers　Western　painting　methods,　resulting　in　less-than-ideal　ink　rendering　effects.　As　a　result,　this　investigation　focuses　on　the　characteristics　of　ink　painting　by　merging　attention　processes　with　three-dimensional　depth　information.　It　emphasizes　differences　in　ink　color　depth　to　depict　the　relationship　between　distance　and　three-dimensional　perception　of　things　in　the　picture.　It　also　makes　use　of　methods　like　line　thickness　and　curves　to　show　the　contours　and　textures　of　things.　Additionally,　to　make　the　picture　as　close　to　the　real　traditional　Chinese　ink　painting　as　possible,　we　use　the　thickness　and　bending　of　lines　to　show　the　outline　and　texture　of　objects,　and　highlight　the　key　points　or　depict　some　details　in　the　picture　by　leaving　blank.　This　method　is　named　FCIGAN　(Freehand　Chinese　Ink　Generative　Adversarial　Network).　We　have　also　gathered　and　created　a　matching　dataset　called　FCI　Images　to　aid　in　the　experiment’s　smooth　progression.　In　conclusion,　the　experimental　results　show　that,　the　FCIGAN　approach　suggested　in　this　research　has　much　better　performance　when　compared　to　conventional　techniques　and　may　be　used　more　effectively　in　the　3D　rendering　field.　©　2024,　Taiwan　Ubiquitous　Information　CO　LTD.　All　rights　reserved.