Twenty years behind the camera, now directing generative imagery. Real products, new worlds, nothing lost in between.
Each row, one project
Packshot → AI scene → detail
A white-background watch packshot turned into a street-style scene in motion. Dial, strap and logo kept intact.
ComfyUI · Nano Banana · Image-to-video
Swiss watches shot in studio, rebuilt in darker worlds. Every gear, screw and engraving preserved.
ComfyUI · LoRA · Flux
A mother-of-pearl watch packshot turned into a soft pink still life with matching jewellery. Dial, links and pearl kept true.
ComfyUI · Nano Banana Pro
Glitter serum in glass: suspended flakes, refraction and label stay true from packshot to campaign.
ComfyUI · Nano Banana
One bottle, two worlds: a sculpted studio set and hard poolside light.
ComfyUI · Flux · Image-to-video
A frayed denim blazer, from ghost mannequin to a model in the street. Fringes, gold buttons and wash kept exact.
ComfyUI · Identity LoRA
Mirror-gold leather that reflects its whole world: the hardest material to keep true in a new scene.
ComfyUI · Image-to-video
Sheer printed chiffon, worn and in motion. Print scale, transparency and drape have to survive the generation.
ComfyUI · Image-to-video
A mini top-handle bag in grained leather. Hardware, stitching and grain checked at macro level.
ComfyUI · Nano Banana Pro
Textured red leather and polished hardware, staged in a bold campaign set.
ComfyUI · Flux
Quilted suede sneakers on a court at golden hour. Nap, quilting and sole kept true.
ComfyUI · Image-to-video
Croc-embossed leather in saturated orange, from packshot to an editorial scene with La Muse.
ComfyUI · Nano Banana
Sportswear shot in studio, then worn by AI models: dawn run, court, brutalist gym. Plus a running loop.
ComfyUI · Image-to-video
A technical cargo trouser, from packshot to a summit at sunrise. Fabric, pockets and fit hold across three AI scenes.
ComfyUI · Nano Banana
Packshot, ghost mannequin or on-model shot on white. Every angle and detail documented, because the AI can only respect what it can see.
ComfyUI workflows combining local and cloud models, LoRA and structured prompts, designed around the brand's visual rules and the volume to deliver.
Product integration, environments and on-model scenes, generated in series with a consistent identity across every view.
Image-to-video loops for campaigns and social: the product keeps its shape, light and details in motion.
Light, perspective, textures, garment drape, anatomy and product fidelity, checked image by image before anything leaves the studio.
I have been a professional photographer since 2007: fashion, e-commerce, luxury, architecture and editorial, including ten years in London.
Today I create commercial imagery with generative AI. I set the art direction for a brand’s visuals, then turn product and on-model shots into campaign-ready scenes, keeping the product, the garment and the model’s identity exactly right. Recent AI work includes e-commerce imagery for Adidas, among other clients.
I design the ComfyUI pipelines behind each project and build my own tools for the hard problems of generative imagery: consistent identity, multi-view generation and virtual casting.