You will get Custom ComfyUI Workflows | SDXL, FLUX, LoRA Training & AI Image Pipelines
Top Rated
Project details
Stop wrestling with node spaghetti - get a ComfyUI workflow engineered to produce exactly the images you need, every time. I will build custom ComfyUI workflows and AI image pipelines around your product, character, or style.
What you get:
• Custom ComfyUI workflows for SDXL, FLUX, and Stable Diffusion
• LoRA training on your character, product, or art style for consistent outputs
• Model fine-tuning, ControlNet, IPAdapter, and upscaling setups
• Batch processing pipelines and API access for automated generation at scale
• GPU optimization: faster generations at lower cost (local or cloud)
• Clean, documented workflow files you fully own, plus a walkthrough video
Use cases: consistent brand characters, product photography at scale, marketing creatives, avatar generators, and image features inside your own app.
I am a senior AI/ML engineer building production image pipelines, not one-off experiments.
Tell me what you need to generate and I will map the exact workflow before we start.
What you get:
• Custom ComfyUI workflows for SDXL, FLUX, and Stable Diffusion
• LoRA training on your character, product, or art style for consistent outputs
• Model fine-tuning, ControlNet, IPAdapter, and upscaling setups
• Batch processing pipelines and API access for automated generation at scale
• GPU optimization: faster generations at lower cost (local or cloud)
• Clean, documented workflow files you fully own, plus a walkthrough video
Use cases: consistent brand characters, product photography at scale, marketing creatives, avatar generators, and image features inside your own app.
I am a senior AI/ML engineer building production image pipelines, not one-off experiments.
Tell me what you need to generate and I will map the exact workflow before we start.
AI Algorithms
Large Language Model, Multimodal Large Language Model, Transformer ModelAI Applications
AI Content Creation, AI Text-to-Image, AI-Generated Art, AI-Generated Video, AIOps, Image Analysis, Image Processing, Image RecognitionAI Development Language
PythonAI Tools
Bing AI, Hugging Face, Jasper AI, PyTorch, TensorFlowAI Models
ChatGPT, DALL-E, GPT-3, GPT-4, Midjourney AI, Stable DiffusionWhat's included
| Service Tiers |
Starter
$450
|
Standard
$800
|
Advanced
$2,000
|
|---|---|---|---|
| Delivery Time | 5 days | 12 days | 25 days |
Number of Revisions | 2 | 3 | 5 |
AI Model Integration | |||
Batch Normalization | |||
Database Integration | |||
Detailed Code Comments | - | ||
Image Upscaling | - | ||
MLOps | |||
Model Deployment | |||
Model Documentation | - | - | |
Model Monitoring | - | ||
Model Testing & Optimization | |||
Model Tuning | - | ||
Natural Language Processing | - | - | |
NLP Tokenization | - | - | |
Pre-Training | - | - | |
Prompt Engineering | |||
Setup File | |||
Source Code |
Frequently asked questions
10 reviews
(9)
(1)
(0)
(0)
(0)
This project doesn't have any reviews.
TM
Tracy M.
Jul 20, 2026
GenAI Engineer for AI Image and Video Generation Pipeline (ComfyUI, Flux, SDXL, Turbo-Z, LoRA)
Exactly what we hoped for. He delivered a complete, production-ready ComfyUI environment with FLUX, SDXL, LoRA support, video workflows, and auto-scaling API endpoints, all documented so clearly that our team was generating images the very same day. He clearly knows this stack inside and out, communicated effectively throughout the project, and delivered everything on time. We'll definitely hire him again in the future.
BJ
Baynton J.
Dec 14, 2025
AI & Data Engineering Specialist Needed for NLP and Deep Learning Projects
Amar did an excellent job. He reviewed and finalized our AI & data engineering system. He quickly understood the existing architecture, fixed NLP and data pipeline issues, and improved overall system stability. Communication was clear, work was well-documented, and everything was delivered on time. We would definitely work with him again for future enhancements.
ME
Mudasar E.
Dec 2, 2025
Senior Generative AI & Automation Engineer | LLMs, Python, n8n, FastAPIs, Webhooks
I rarely write long reviews, but the quality of work I received truly deserves it.
I hired him for a highly complex project involving Generative AI, LLM integrations, and automation workflows, and he exceeded all my expectations. I needed someone to wrap up the project for me, and I’m genuinely glad I found the right person.
I hired him for a highly complex project involving Generative AI, LLM integrations, and automation workflows, and he exceeded all my expectations. I needed someone to wrap up the project for me, and I’m genuinely glad I found the right person.
KH
Kimberly H.
Mar 3, 2025
Grafana Expert
MR
Merlo R.
Dec 3, 2024
get all the estimates whose status is sent through this API call
Amar was awesome to work with. He replied to all of our asks and made everything very easy for us
About Amar
Multimodal AI Engineer | GenAI, AI Image/Video Pipelines, ComfyUI/LoRA
100%
Job Success
Lahore, Pakistan - 6:22 pm local time
Most AI projects don't fail at the idea stage - they stall at 80%. The prototype works, then it never becomes a product clients can trust: characters drift between images, outputs break schemas, accuracy is a guess. That last stretch - consistency, structured outputs, evaluation, real deployment - is exactly what I do. 10+ years in software, now focused entirely on Multimodal and Generative AI.
𝐖𝐡𝐚𝐭 𝐈 𝐁𝐮𝐢𝐥𝐝:
- Multimodal AI pipelines: end-to-end systems combining LLM story/content generation (structured JSON schemas) with image generation - identity-locked characters across hundreds of pages, outfit consistency, emotion and expression control, multi-character scenes, reference-image workflows.
- AI image generation pipelines: ComfyUI, Flux / FLUX.2, SDXL, Nano Banana - with LoRA training (Kohya, ai-toolkit), ControlNet, IPAdapter, PuLID/InstantID face locking, inpainting, and Runware/API-based generation for production consistency and quality control.
- AI video generation pipelines: image-to-video and text-to-video using WAN 2.2, LTX, Kling, Veo, Runway, Seedance - plus audio-driven lip-sync, talking avatars, and motion-controlled animation systems.
- AI UGC and ad creatives: scroll-stopping product showcase videos, UGC-style ads, and short-form marketing content for TikTok, Reels, and Meta campaigns - built as repeatable AI pipelines, not one-off edits.
- Audio & speech: Whisper speech-to-text, ElevenLabs TTS and voice cloning, photo & audio to talking-avatar video pipelines.
- LLM & VLM integration: GPT-4o/5-class vision, Claude, Gemini integrated into business systems - structured outputs, schema validation, RAG with LangChain/LangGraph and vector DBs (Pinecone, FAISS).
- LLM/VLM Evals & quality optimization: golden datasets, LLM-as-judge and VLM-as-judge scoring, experiment-driven prompt optimization, regression testing with Langfuse/Promptfoo/Braintrust - so accuracy becomes a tracked number ("71% to 84% in three cycles"), not an opinion.
- AI agents & automation: multi-step agents with CrewAI, AutoGen, MCP integrations, and n8n workflows with LLM-powered decision-making.
- Full-stack developments: React/Next.js frontends, Node.js/FastAPI backends, PostgreSQL - so your AI product ships as one system, not disconnected pieces.
- Deployment: FastAPI backends, Docker, CI/CD for ML pipelines, GPU queue serialization, cost-efficient serverless inference on RunPod/Modal.
𝐑𝐞𝐜𝐞𝐧𝐭 𝐖𝐨𝐫𝐤:
✔️ 𝗣𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗲𝗱 𝗔𝗜 𝗦𝘁𝗼𝗿𝘆𝗯𝗼𝗼𝗸 𝗣𝗹𝗮𝘁𝗳𝗼𝗿𝗺: children's book illustration pipeline - hero photo & child's details in; stylized character reference, structured 15-page story JSON, and identity-consistent page illustrations out (Flux & Runware). Personalized storybooks with character, outfit, and expression consistency at production scale.
✔️ 𝗗𝗔𝗧𝗔𝗦𝗜𝗠: AI character generation platform with dual ComfyUI pipelines, automated LoRA training, quality gating, and GPU queue serialization - thousands of identity-locked images.
✔️ 𝗩𝗟𝗠 𝗔𝗰𝗰𝘂𝗿𝗮𝗰𝘆 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻: eval pipeline for a food-photo-to-calories feature - golden dataset, automated scoring, experiment-driven prompt iteration to lift real accuracy.
✔️ 𝗝𝗼𝘆𝗣𝗶𝘅: AI talking-video platform - photo & audio in, lip-synced avatar video out, identity preserved at scale.
✔️ 𝗛𝗶𝗿𝗲𝗛𝗮𝗿𝗿𝘆: multi-agent AI platform backend - LLM task automation with production-safe structured outputs and deterministic state transitions.
You'll get daily updates, clear milestones, and a fully documented handover - so your team can run the system without me. If your project involves multimodal AI, image or video generation pipelines, LLM/VLM integration, evals, or getting any of it actually deployed and reliable - send me the details and I'll tell you exactly how I'd build it.
𝐓𝐞𝐜𝐡: ComfyUI, Flux, FLUX.2, SDXL, Nano Banana, Stable Diffusion, LoRA, Kohya, ai-toolkit, ControlNet, IPAdapter, PuLID, InstantID, Runware, WAN 2.2, LTX, Kling, Veo, Runway, Seedance, HeyGen, Wav2Lip, Whisper, ElevenLabs, TTS, FFmpeg, PyTorch, OpenCV, GPT-4o, Claude, Gemini, Llama, LangChain, LangGraph, RAG, Pinecone, FAISS, CrewAI, AutoGen, MCP, n8n, Langfuse, Promptfoo, FastAPI, Python, Node.js, React, Next.js, PostgreSQL, Docker, RunPod, Modal, AWS.
Note: I don't take on NSFW, adult, or explicit content projects.
Steps for completing your project
After purchasing the project, send requirements so Amar can start the project.
Delivery time starts when Amar receives requirements from you.
Amar works on your project following the steps below.
Revisions may occur after the delivery date.
Requirement Analysis & Workflow Design
I will review your content goals, reference images, and output requirements. Design the node architecture and select optimal models (SDXL, FLUX, ControlNet, LoRA).
LoRA Training & Model Preparation
If needed, I will train custom LoRA models on your images for consistent identity/style. Prepare all checkpoints, embeddings, and custom nodes required.