I’m a creator who enjoys experimenting with emerging technologies, blending traditional artistic elements with AI tools to explore new visual possibilities. This project began with an experimental idea: fusing a cappella vocals with shamisen and pairing it with stylized visuals. The workflow started with Suno, generating music and using its editing tools to adjust each section and gradually refine the sound. For visuals, I used Flux to generate images, but converting them to video presented challenges— maintaining ink-wash style consistency was difficult. Human characters gradually shifted toward photorealism, so I switched to animal characters: a crane and an ape. Even with animals, adjustments were needed. I applied geometric processing to the characters through image editing tools to create more blocky shapes, hoping to maintain character consistency. This brought slight improvements in temporal drift, though generating quality videos remained challenging. Each video model has its strengths, requiring different strategies for different scenes. For the ape’s delicate shamisen playing, Veo performed best with accurate motion and physics. However, stylized characters sometimes drifted, so to maintain visual consistency, I kept the ape seated with minimal large movements. The crane was particularly tricky—it needed dynamic action without visually falling apart. Sora excelled here, producing story-driven visuals with fluid motion. Sometimes the crane stretched or bent in exaggerated ways, which actually aligned with classic animation principles like squash and stretch. The still ape and the frantic crane created a striking contrast, with the push and pull between calm and chaos giving the story more power. The entire process involved trial and error, with constant surprises—sometimes exciting, sometimes unsettling. Direction wasn’t always clear, but staying flexible and experimental helped the project gradually come together. “So Close Yet So Far” is a rhythmic, experimental music video that blends Eastern and Western elements, following a crane and an ape as it explores the theme of endless pursuit without fulfillment. The story centers on a crane relentlessly chasing fruit, while in another scene, an ape plays the shamisen. Though occupying different spaces, the two characters create a dialogue through music and editing, establishing a resonance between pursuit and observation, motion and stillness. The film is rendered in ink- wash style, evoking traditional East Asian aesthetics while incorporating the dynamic capabilities of modern AI technology. The music fuses a cappella vocals with shamisen, an unusual East-West instrumental combination that mirrors the visual blend of traditional art and contemporary digital creation. The editing synchronizes with musical beats, allowing visuals to respond to and amplify the auditory experience. The visual approach employs a multi-model strategy. The ape was generated using Veo, which excels at handling delicate movements and physics. To prevent style drift, the ape remains seated with minimal large movements—a restraint that not only solves technical limitations but also shapes a calm, focused character. The crane was generated using Sora, which produces story-driven, fluid motion. Sometimes the crane stretches or bends in exaggerated ways, unexpectedly aligning with traditional animation principles of squash and stretch, adding vivid expressiveness to the character. Plant transformation scenes were created using Kling’s First Frame to Last Frame feature, with natural, fluid ink-wash style blending that adds a magical, poetic atmosphere to the film. The still ape and frantically chasing crane create a striking contrast. This push and pull between calm and chaos, focus and obsession, becomes the film’s core tension. Though in different scenes, the ape’s performance seems to provide a soundtrack to the crane’s chase—both parallel narrative and emotional counterpoint. Thematically, the crane presents the dilemma of endless pursuit without attainment—things that seem within reach yet remain forever beyond grasp. The ape represents an alternative state: immersion in the present moment. The production process involved constant trial and error, with direction not always clear, but flexibility and experimental spirit allowed the project to take shape. Through dynamic editing, the collision of Eastern and Western musical elements, and the use of multiple AI tools, it creates an experience that is both visually striking and poetically resonant. Through animal characters and abstract narrative, each viewer can find their own projection and understanding within it.