LoRA & Diffusion Model Fine-tuning
I train custom LoRAs and fine-tune diffusion models for VFX-specific styles, HDR output, and character consistency on my RTX 5090 32GB.
Models I Train
Image Generation
Video Generation
Training Tools I Use
My go-to for complex training configs. Full control over every parameter.
Quick Flux LoRA training. Best for rapid iteration.
When I need Prodigy optimizer and advanced schedulers.
My Captioning Pipeline
Built a custom captioning tool using Gemma 3-12B via vLLM. Concurrent batch processing gives me 50+ images/min - 10x faster than BLIP-2.
What I Train For
VFX Style Matching
Training models to match specific film looks and color grades for concept art.
Character Consistency
LoRAs for consistent character appearance across storyboard generations.
HDR Output
Fine-tuning for LogC4/ACEScg color spaces for professional VFX integration.
Custom Assets
Training on proprietary environments, props, and styles for studio work.
Technology Stack
Expertise by Sumit Chatterjee
Industrial Light & Magic, Sydney