Midhun Harikumar

ML Lead and Engineering Manager at Morphic

I lead ML efforts at Morphic as both ML Lead and Engineering Manager. My team builds zero-shot character customization, camera controls, and video outpainting/inpainting for video diffusion models.

Previously at Adobe, I was a founding member of Adobe Firefly and deployed Adobe's first production diffusion model to Photoshop as tech lead. I worked on controlled image generation, led zero-shot customization efforts, and managed the enterprise foundational model team for model customizations.

Outside of work, I have a keen interest in DIY electronics, Physical AI, and the history of science. I also follow Formula 1 and the World Endurance Championship racing series.

LinkedIn | Google Scholar | X


Publications

Reshoot Anything: A Self-Supervised Model for In-the-Wild Video Reshooting

CVPR 4D World Models Workshop 2026

Precise camera control of video diffusion models using self-supervised dataset generation strategy and training without synthetic pairs.

TexSliders: Diffusion-Based Texture Editing in CLIP Space

ACM SIGGRAPH 2024

A novel framework for semantic texture manipulation by leveraging the latent space of pretrained diffusion models and CLIP embeddings. Enables fine-grained control over texture attributes while preserving structural integrity.

PREDITOR: Text-Guided Image Editing with Diffusion Prior

A novel approach for text-guided image editing that utilizes diffusion priors to achieve semantically meaningful modifications while maintaining image coherence and photorealism.

Enhanced Controllability in Diffusion Models through Feature Disentanglement

ICML 2024

An innovative architecture for diffusion models that separates spatial content and style representations, leading to improved manipulation capabilities and more precise control over generated outputs.


Patents

19 granted US patents — Adobe Inc., Amazon Technologies

2026

PatentTitle
US 12,596,766Automatically generating an image dataset based on object instance similarity
US 12,586,271Color conditioned diffusion prior
US 12,586,259Image generation using a text and image conditioned machine learning model
US 12,579,608Generating tile-able patterns from text
US 12,555,288Controllable diffusion model
US 12,536,722Utilizing a diffusion neural network for mask aware image and typography editing
US 12,530,822Utilizing a diffusion prior neural network for text guided digital image editing

2025

PatentTitle
US 12,511,877Object-agnostic image representation
US 12,493,937Prior guided latent diffusion
US 12,406,334Preset style transfer
US 12,322,007Systems and methods for color palette optimization
US 12,299,939Generating novel images using sketch image representations
US 12,277,630Unsupervised style and color cues for transformer-based image generation
US 12,260,480Machine learning-based layout generation (also CN, AU, DE)

2024

PatentTitle
US 12,008,698Image segmentation using text embedding
US 11,934,448Keyword localization digital image search

2023 and earlier

PatentYearTitle
US 11,574,3922023Automatically merging people and objects from multiple digital images
US 11,138,2572021Object search in digital images
US 10,789,5692020System to determine item footprint (Amazon)