Orthodontics is a field of dentistry that focuses on correcting misaligned teeth. Orthodontic treatment often involves the use of braces, aligners, retainers, and other dental appliances to align teeth, correct bite issues, and improve overall dental health and aesthetics. But fixing them can be a long and complicated process. So, it’s important to have a picture showing what your teeth will look like after treatment. This helps dentists explain things better and makes patients more likely to go through with the treatment. In this paper, we present an approach for generating the conditional image of a misaligned tooth to an aligned tooth from a diffusion model it takes 2D images as input (e.g., captured by the camera, or smartphones), and aligns the teeth part in the image within 2D image space to generate post-treatment like images, our method employs 3D STL data scanned by intra-oral scanner projecting pre- and post-treatment, diffusion model to learn the spatial movement of each tooth followed by post-processing to convert the teeth area more realistic textures. We validate our pipeline over various facial photographs, illustrating its outstanding effectiveness and broad utility within the field of Orthodontics.