Artist Technician – Generative Video & ComfyUI Specialist
Latent Space Media
Category:
Film & Video ProductionRequired AI Tools:
Job Description
We’re looking for a creative and technically savvy Artist Technician with strong experience in ComfyUI, AI-powered video generation, training of loras, custom workflow creation and finetuning. This role is ideal for someone who thrives at the intersection of film making, art, and generative media—building smart, scalable pipelines to turn creative visions into stunning video outputs.
As a remote hourly contributor, you’ll support creative teams by building and refining workflows that leverage the latest in generative AI technology, with a focus on high-quality, customizable video content.
Key Responsibilities:
Build and manage complex ComfyUI workflows for generative video production.
Create finetuned workflows for processes such as inpainting, first frame i2v, first and last frame i2v, keyframe i2v, v2v multi-controlnet, foreground/background separation, and lip syncing.
Collaborate with creatives and production leads to develop pipelines that align with visual direction and storytelling needs.
Troubleshoot and maintain software consistency across all workstations. Training of custom Loras for integration into production workflows
Integrate tools like API Nodes, Framepack, Recamaster, ControlNets, Flowedit, Hooks, and Fantasy Talking into seamless video workflows.
Automate and document processes to improve consistency and output efficiency. Stay up to date with the latest model releases, extensions, and experimental techniques in the generative video space.
Required Skills: Expertise in ComfyUI, including custom workflow design and custom node usage.
Experience with AI video generation tools (e.g., Wan 2.1, LTX, Flux, AnimateDiff, ControlNets, Model training, Runway, Kling).
Solid understanding of video processing techniques, including masking, frame interpolation, upscaling, and visual effects.
Proficiency in Python, with a focus on AI-related libraries and packages. Experience deploying and executing AI/ML models locally and on enterprise-grade server systems, optimizing for both environments.
Working knowledge of Windows and Linux systems management.
Ability to work independently, meet deadlines, and communicate clearly in a remote setting.
Portfolio of relevant work or demo reels showing generative image and video projects.
Nice to Have: Hands-on experience training custom AI checkpoints for various model architectures, including image and video processing.
Experience with video editing and VFX software (e.g., After Effects, DaVinci Resolve, Nuke).
Knowledge of 3D or interactive tools like Blender, Unreal Engine, or TouchDesigner.
Interest in ethical considerations and best practices in AI-generated media.
What We Offer: Fully remote, flexible working hours with visits to Beacon, NY
Opportunities to experiment with the latest generative AI tools.
A collaborative, forward-thinking team passionate about merging art and technology.
_*This job board features a curated list of industry-specific roles aligned with the skill sets taught in Curious Refuge programs. Curious Refuge is not responsible for any arrangements or agreements made between employers and candidates. Please note that Curious Refuge does not act as a mediator and is not liable for any part of the engagement, transactions, or outcomes. We strongly encourage candidates to exercise caution and conduct proper due diligence before sharing sensitive information and/or agreeing to work._