This section showcases the workflow behind my AI-generated visuals and videos — from concept development and prompt engineering to cinematic transitions and narrative-driven motion design.
AI Workflow
My AI workflow combines prompt engineering, image generation, and cinematic storytelling to rapidly explore concepts, build visual narratives, and accelerate creative production.
I primarily use ChatGPT for prompt engineering and creative direction — combining structured text prompts with image references to refine visual style, mood, composition, and storytelling consistency. This process allows for faster iteration and more controlled creative outputs.
For image generation, I initially worked with Sora, before transitioning to Google Gemini as my main tool for generating visual concepts and exploratory imagery.
For motion and video generation, I use Kling AI alongside Midjourney to create cinematic transitions and visual sequences. A common workflow involves generating two keyframes in ChatGPT, then using Kling to transition between them. To achieve smoother and more intentional motion, I create detailed transition prompts in ChatGPT that describe camera movement, atmosphere, pacing, lighting, and scene evolution — transforming static visuals into cohesive narrative moments.
This workflow allows me to blend creative direction with rapid experimentation, turning ideas into scalable visual concepts across image, motion, and storytelling formats.
AI Workflow
My AI workflow combines prompt engineering, image generation, and cinematic storytelling to rapidly explore concepts, build visual narratives, and accelerate creative production.
I primarily use ChatGPT for prompt engineering and creative direction — combining structured text prompts with image references to refine visual style, mood, composition, and storytelling consistency. This process allows for faster iteration and more controlled creative outputs.
For image generation, I initially worked with Sora, before transitioning to Google Gemini as my main tool for generating visual concepts and exploratory imagery.
For motion and video generation, I use Kling AI alongside Midjourney to create cinematic transitions and visual sequences. A common workflow involves generating two keyframes in ChatGPT, then using Kling to transition between them. To achieve smoother and more intentional motion, I create detailed transition prompts in ChatGPT that describe camera movement, atmosphere, pacing, lighting, and scene evolution — transforming static visuals into cohesive narrative moments.
This workflow allows me to blend creative direction with rapid experimentation, turning ideas into scalable visual concepts across image, motion, and storytelling formats.