AI Media Engineer for Automated Media Generation

We are seeking an expert AI Media Engineer to develop an automated AI media generation system. The role involves designing and implementing AI models for video and audio synthesis, integrating with existing systems, and optimizing performance. The ideal candidate will have experience with AI media generation tools and a strong understanding of AI engineering principles. Title: AI Media Engineer — ComfyUI, SDXL, Flux, LTXVideo, CogVideoX, ElevenLabs, FastAPI, NVIDIA GPU, Docker Building an automated AI media generation pipeline on a local GPU server (NVIDIA). Need a specialist to install ComfyUI and build image and video generation pipelines exposed via API. All in Docker, accessible via VPN only. Scope: - ComfyUI setup: install on Ubuntu with NVIDIA GPU in Docker, SDXL/Flux (image), LTXVideo/CogVideoX (video), API mode enabled - Image pipeline: consistent character reference, FastAPI endpoint /generate/image - Video pipeline: 8-second segments, consistent character across segments, no freeze transitions between segments, FastAPI endpoint /generate/video - Voiceover: ElevenLabs integration, apply audio to video segments, FastAPI endpoint /generate/voiceover Deliverables: - ComfyUI running in Docker with GPU validated - Image endpoint working and tested - Video endpoint with consistent character and no freezes - ElevenLabs voiceover integration - Docker Compose and README - Sample outputs: 3 images and one 24s video (3x8s) Required: ComfyUI custom workflows, image and video generation models, NVIDIA GPU on Linux, FastAPI, Docker Timeline: 2-3 weeks, fixed price To apply: share ComfyUI workflow examples, your experience with consistent character generation, and your price.