Comfy Ui (Gen Ai) Specialist/Developer

We are an early-stage startup operating at the intersection of generative AI, digital media, and publishing. This role offers significant entrepreneurial and creative freedom within a fast-moving environment. You will have the opportunity to apply your existing technical expertise while developing highly relevant skills in a rapidly emerging sector where virtual influencers and AI-generated personas are increasingly reshaping digital media.

We are looking for an experienced ComfyUI specialist to design and operate a scalable generation pipeline capable of producing several hundred consistent character images per day across multiple distinct characters, as well as short video clips.

This is a technical production role, not a prompt-engineering position. The ideal candidate can design modular, reusable ComfyUI workflows, implement batch automation, manage LoRAs and seeds for character consistency, and optimize GPU/VRAM performance for high-throughput output.

Required expertise:

• Advanced ComfyUI workflow architecture
• LoRA training and integration
• ControlNet, IPAdapter, embeddings, checkpoint management
• Automation logic (CSV/JSON-driven prompts, structured outputs)
• GPU optimization and remote server environments (SSH, hosted GPUs)

Experience with AnimateDiff or Stable Video Diffusion and maintaining identity consistency across frames is strongly preferred.

You must be comfortable working with unrestricted Stable Diffusion checkpoints.

This is ongoing work with long-term potential.

To apply, please share:

• Portfolio demonstrating consistent multi-character outputs (image + video if available)
• Brief overview of your ComfyUI setup and hardware/cloud environment
• Your rate and availability

Only candidates with demonstrable production-level experience will be considered.