ComfyUI Artist / AI Video & Image Pipeline Specialist

Infolabs Global · India

ComfyUI Artist / AI Video & Image Pipeline Specialist

Company: Infolabs Global

Location: Remote / Work From Home

Type: Full-time (Contract-based)

Compensation: ₹40,000 – ₹70,000 / month

Experience Required: 1.5 – 2 years hands-on with ComfyUI

About the Role We are seeking a skilled ComfyUI Specialist to join our creative production pipeline at Infolabs Global. We produce high-quality, storyboard-driven video content. The process involves taking a storyboard or reference input, generating key images, and animating them into a series of short clips (typically 10–15 clips of 10–15 seconds each per project). We already have robust workflows built out; you will be the core operator who runs, troubleshoots, and evolves them as our production needs grow.

What You'll Do

• Take a storyboard or creative brief and execute it end-to-end: generate images, then animate them into short video clips following our established pipeline.
• Manage multiple clips per project (10–15+ per storyboard) while maintaining visual and narrative consistency across the entire set.
• Operate and maintain our existing ComfyUI workflows—troubleshoot issues, fix broken nodes, and optimize performance.
• Update and adapt workflows dynamically as new requirements, tools, or models emerge.
• Work confidently across both image generation/editing and image-to-video or text-to-video pipelines.
• Flag and solve problems independently when a workflow breaks, encounters dependency issues, or produces unexpected visual results.
• Collaborate with the creative and art teams to match style, tone, and output quality expectations.

What We're Looking For

• 1.5–2 years of hands-on experience with ComfyUI: You must understand how nodes, samplers, and custom workflows actually work under the hood, rather than just running pre-made templates.
• Image Generation Expertise: Strong working knowledge of image generation and image editing models (inpainting, image-to-image editing, style transfer, etc.).
• Video Model Experience: Solid practical experience with video generation models and image-to-video workflows (FLUX, FLF, Stable Video Diffusion, Kling, or similar tools).
• Ecosystem Adaptability: Comfortable working with a variety of open-source and commercial models in the current AI image/video ecosystem, and quick to pick up new ones as the space evolves.
• Debugging Skills: Ability to troubleshoot and fix broken workflows, custom nodes, dependency issues, and version conflicts.
• Visual Storytelling: A good eye for visual quality, consistency, and narrative flow through generated imagery.
• Asset Management: An organized approach to managing multiple assets and clips within a single overarching project.
• Advanced Techniques: Direct experience with ControlNet, LoRA training/usage, or building custom workflows from scratch.

Nice to Have

• Familiarity with prompt engineering tailored specifically for both static images and video motion.
• Experience working in a fast-paced production environment with tight turnarounds.

How You'll Work We have structured, proven workflows already in place—you will not be starting from zero. Your objective is to execute within that structure reliably, understand it deeply enough to fix it when something breaks, and actively help refine it as our AI processes mature over time.

How to Apply If you have the technical depth to manage complex node trees and the creative eye to produce stunning video content, we want to hear from you.

Please send your resume, a brief overview of your ComfyUI experience, and a portfolio or examples of your AI video generation work to hr@infolabsglobal.ai .