Diffusion Experties
• Dataset creation
• Model fine-tuning
• Lora training
• Workflow automations
• Dynamic prompt workflows
• Multi-step image processing
LLM Utilisation
• Dataset creation
• Rule-based prompting systems
• Workflow optimization and automation through tool creation
AI Audio Experties
• Audio dataset creation
• TTS model finetuning
• VTV model training
• VTV model merging
• Multi-step TTS to VTV audio generation
Image Generation and Processing
My work with image diffusion models has revolutionized my approach to visual design. By integrating these tools into my current software packages like Blender and Adobe Photoshop, I’ve developed efficient workflows that dramatically reduce project completion times while maintaining high or higher-quality outputs. From automating texture creation in 3D modelling or bypassing the rendering process entirely to streamlining photo editing processes and accelerating concept development for logos and graphics.
Language Model Integration
Large Language Models (LLMs) serve as powerful assistants in my design process, enabling the creation of specialized tools and automated workflows that enhance productivity across projects. I leverage these models to generate datasets, develop rule-based prompting systems, and create custom solutions for specific design challenges. Through custom node development and workflow optimization, I’ve established efficient processes that maintain consistency while reducing the time invested in repetitive tasks.
AI Voice Production
My work with AI audio technologies has expanded my multimedia capabilities, particularly in the areas of Text-to-Speech and Voice-to-Voice. Through the use of various open-source models and tools, I’ve developed workflows for creating custom realistic voice-overs and audio content for video projects. Allowing me to produce quality voice content that complements my visual design work.