ComfyUI / Stable Diffusion engineer
1 day ago

Job description
I'm looking for an experienced ComfyUI / Stable Diffusion engineer to set up a production-ready AI video workflow on a VPS server.
This is NOT a prompt engineering job.I need a clean, scalable system for commercial product video generation.
Phase 1 – Initial Setup
1. Install and fully configure ComfyUI on my VPS (GPU-ready).
2. Install required video extensions (AnimateDiff / Stable Video Diffusion or best alternative).
3. Optimize for stability and performance.
4. Ensure commercial-safe models.
Environment must be:
- Stable
- Documented
- Backed up
- Easy to maintain
Phase 2 – Build Product Video Pipeline (Coffee Cups)
Create ONE solid pipeline for generating commercial product ads.
Input:
– Static product image (coffee cup)
Output:
– 4–6 cinematic lifestyle scenes
– Realistic lighting
– Consistent product geometry
– 9:16 (Meta Ads) + 1:1 export
– Clean upscale-ready output
Requirements:
- Product consistency (shape must not distort)
- Easy product swap (replace image, keep workflow)
- Organized node structure (no chaos)
- Performance optimized
- Clear naming inside nodes
Deliverables
- Fully working ComfyUI installation on VPS
- Clean workflow JSON file
- Documentation (PDF or Notion)
- 15–20 min Loom video explaining how to use it
- Basic backup instructions
Future Work
After initial pipeline:
- Add variations (gym scene, office, travel, minimal studio)
- Add batch generation
- Possibly build simple front-end UI
⸻
To Apply
Please provide:
- Examples of ComfyUI workflows you built
- Screenshots of node-based setups
- Experience with AnimateDiff or Stable Video Diffusion
- Estimated timeline
- Estimated budget
Contract duration of less than 1 month. with 30 hours per week.
Mandatory skills:
Artificial Intelligence, Python, Generative AI, Generative AI Prompt Engineering, AI Video Generation, AI Image Generation, LoRa, Stable Diffusion, AI Model Development, AI Model Training, Automated Workflow, AI-Generated Art, Photorealistic Rendering, AI Text-to-Image, Social Media Content Creation
Similar jobs
Diffusion Process Engineer responsible for multiple processes in a high-volume manufacturing facility. · ...
2 weeks ago
We are seeking a Senior Machine Learning Engineer to advance the state of learned reconstruction for Replica. In this role, you will drive development of feed-forward and diffusion-based models for 3D and spatiotemporal reconstruction and work closely with cross-functional teams ...
1 month ago
Parallel Domain is building a simulation platform for autonomy and robotics. · We are seeking an experienced Senior Machine Learning Engineer to drive development of feed-forward and diffusion-based models. · The successful candidate will design innovative ML models, · improve sc ...
1 month ago
We are seeking a Senior Machine Learning Engineer to advance the state of learned reconstruction for Replica. · Develop innovative ML models: Design and implement video-to-video diffusion models and efficient 4D feed-forward reconstruction methods. · Improve scalability and perfo ...
1 week ago
We are seeking a Senior Machine Learning Engineer to advance the state of learned reconstruction for Replica.In this role, you will drive development of feed-forward and diffusion-based models for 3D and spatiotemporal reconstruction and work closely with cross-functional teams t ...
1 month ago
Machine Learning Engineer for Image Diffusion Models
Only for registered members
We are seeking a skilled Machine Learning Engineer with a strong background in building and deploying image diffusion models. · Training and inference processes · ...
3 weeks ago
AI Engineer Needed – Stable Diffusion + ControlNet for Artistic QR Code Generation
Only for registered members
+Job summary · We are looking for an experienced AI / ML Engineer to help us build a system that generates high-quality artistic QR codes while keeping them fully scannable. · The solution should combine Stable Diffusion with ControlNet (QR-based models) to produce artistic QR im ...
3 weeks ago
We are building a private, · trainable,diffusion-based video generation system focused on cinematic · talking humans.We are looking for deep model-level expertise and ownership. · ...
1 month ago
A qualified 3D Designer/Mechanical Engineer is sought to develop a functional prototype for a unique bottle top. · Develop a functional prototype for a hybrid Aero-Diffuser bottle top. · ...
1 month ago
Senior Backend/ ML Engineer for Video Cloning Platform
Only for registered members
We're building a next-generation AI video platform focused on high-fidelity avatar video, · custom voice cloning and identity cloning. · Extend ComfyUI workflows for video generation · Customize and chain diffusion models (image,video,audio,lipsync) · ...
2 weeks ago
Circuit Design for Piezoelectric Aroma Diffuser
Only for registered members
We are seeking an experienced electrical engineer to design a circuit that will effectively drive a piezoelectric disc for an experimental aroma diffuser. · ...
2 weeks ago
+We are seeking an experienced AI Avatar Pipeline Engineer to develop and optimize our avatar creation pipeline utilizing Stable Diffusion LoRA, 3D Graphics Systems (3DGS), and Unreal Engine 5. · ...
1 week ago
AI Graphics Prototype Engineer Needed for ComfyUI and SDXL Projects
Only for registered members
I'm building a personalized children's book platform that converts real family photos and written stories into fully illustrated character-consistent storybooks. · ...
1 week ago
We are looking for an experienced 3D motion graphic developer to validate large capacity video project files and provide a technical assessment on project file manageability. · Unreal Engine · Houdini · ...
1 month ago
We are developing a high-end artificial lighting system that realistically simulates natural daylight for indoor spaces (gyms, offices, basements, commercial interiors) · Design a ceiling-mounted lighting system that: Feels like real daylight not LED light · Has even distribution ...
1 month ago
AI Engineer Needed for Advanced Image Generation Pipeline
Only for registered members
We are building a production-grade image generation service using modern diffusion models. You will be working on a multi-stage, API-driven inference pipeline with strict requirements around identity consistency, pose control, and masked refinement.You'll be implementing and refi ...
1 month ago
We are looking for an experienced AI engineer who has worked on image-to-video generation systems. · Contract duration of more than 6 months. · ...
1 month ago
3D Product Animation – Airflow Visualization for Diffuse-Air Technology
Only for registered members
We are looking for a skilled 3D product animation specialist to create a short, high-quality animation that visually explains our proprietary Diffuse-Air technology. · Diffuse-Air is an innovation designed to improve how air flows through hair rollers by distributing airflow more ...
1 month ago
We are looking for an experienced GenAI Python ML Engineer to develop and deploy Generative AI models for text, image and multimodal applications. The successful candidate will have experience with frameworks like TensorFlow and PyTorch and strong knowledge of NLP and deep learni ...
1 week ago
We are Bagel Labs, a distributed machine learning research lab working towards open-source superintelligence. · Every requirement below is flexible for a candidate with high enough agency and tolerance for ambiguity. · You will design, build, and relentlessly optimize the infrast ...
1 month ago