AI Lab

Experiments in generative visuals, custom workflows, and model training

What is AI Lab?

The AI Lab is an ongoing space for research, experimentation, and workflow development at the intersection of motion design and generative systems.
Here, I explore how AI-driven image and video tools can be integrated into professional motion design pipelines — focusing on control, repeatability, and visual consistency. The work ranges from abstract visual studies to system-based experiments, often built through multi-stage workflows combining generative models, animation, and traditional compositing.

Looping Explorations

A series of looping animations developed from a single starting image. The process explores how generative image editing, multi-stage animation, and traditional compositing can be combined into a controllable, repeatable workflow. Keyframes were generated using Qwen image-edit models, expanded into sequential animations, assembled in After Effects, and refined through temporal cleanup and upscaling passes to produce seamless high-resolution loops.
Tools used: ComfyUI, After effects
Models: Qwen Image Edit, WAN2.2, VACE

Day in the life

Around the World

Bounce

Textures

Visual Explorations

Tools Used: ComfyUI, WAN, Qwen Image, Qwen Edit, Custom LoRAs
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder

Camera Movement Transfer using Uni3c

Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder
Mobirise Website Builder

Style Transfer Explorations using SDXL and IP-Adapter

Start
Initial Image
1
Crayon
02
Whiteboard Marker
03
Oil Painting

Early Video to Video Style Transfer Explorations

Tools Used: SD1.5, IP-Adapter, AnimateDiff, ComfyUI
Start
Source Video
1
Stylized Video

AnimateDiff and SD1.5 Explorations

Start
1
02
03

© Copyright 2025 AshmoTV - All Rights Reserved