The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
For this challenge, I designed a fictional luxury skincare brand (SV serum) and used Melius to build a complete production pipeline from one product photo. The workflow branches into seven parallel creative directions...Each shot uses a different visual storytelling approach while maintaining product consistency across all seven outputs. The workflow uses multiple models (GPT Image 2, Nano Banana Pro, Seedance 2.0, Kling 3.0) routed by Mel based on the creative needs of each shot photorealistic models for editorial work, generative models for sensory textures, and video models for motion clips.This workflow replaces what would traditionally require a full production team, studio time, and a five-figure budget. One product image in. A complete multi-format brand campaign out.....View workflow here Melius Workflow
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Project NOVA is a retro-futurist mobility brand reimagining motherhood through cinematic design, luxury innovation, and emotionally driven stroller concepts inspired by vintage visions of the future.
I really enjoyed using Melius throughout this project, especially how quickly the platform was able to generate outputs once I prompted the agent. What impressed me most was how much it could create from a single idea — it helped generate an entire brand world including branding, advertisements, visuals, and videos in a very short amount of time. As someone who used to spend hours creating decks and creative presentations manually, I immediately saw how much time a tool like this could save during the ideation and creative development process.
This was also my first time using a platform like Melius to build a concept from scratch. I still struggle at times with prompt writing, but I appreciated how Melius helped translate ideas into more complete prompts and visual directions, which made the process feel much more approachable and collaborative creatively.
One area I think could improve is onboarding and tool education. I would have loved more information or tutorials explaining the available tools, node types, and ways to organize workflows on the canvas. I occasionally felt a little lost while trying to structure and manage my workspace. I also wasn’t initially aware of how the credit system worked, so I ended up using a large portion of my credits during an experimentation phase while learning the platform and exploring different creative directions.
Overall, I found Melius to be an incredibly inspiring creative tool that made the process of world building, concept development, and visual storytelling feel much faster and more accessible.
My process
Began with the idea of designing a futuristic stroller concept that solved real frustrations modern mothers experience in everyday life, including navigating stairs, weather protection, storage limitations, and mobility.
Explored multiple futuristic mobility concepts before narrowing the direction into a retro-futurist stroller brand inspired by vintage visions of the future, cinematic editorial campaigns, and luxury industrial design.
Used Melius agents and multiple workflow nodes to experiment with visual styles, prompt refinement, atmosphere direction, and feature ideation while developing the overall world and identity of Project NOVA.
Iterated through different stroller forms, materials, silhouettes, and environments to balance futuristic innovation with emotional warmth, functionality, and stylish motherhood aesthetics.
Developed multiple concept models within the Project NOVA universe, including stair-climbing mobility, hover functionality, weather-adaptive shielding, and self-driving companion stroller systems.
Refined the final visuals and branding direction around retro futurism, blending 1950s-inspired optimism, cinematic storytelling, luxury mobility design, and modern motherhood.
Nice work!
So only one entry allowed but I did worked on a second flow to get my wits about me. This one was for a cream that would have a SPF and healing properties for different skin conditions all in one cream.
Forgot to mention in my initial post that I liked the agent drawing and adjusting the whole board when prompted with certain overall brand changes. The was very apparent and more consistent in this flow, and I felt it kept things pretty cohesive with generation.
Looks like nice work.
Title:
The Graphic Novel Syndicate: A Fully Automated 60-Page Production Pipeline
Project Link: [https://app.melius.com/projects/c95de835-b21e-42cb-b77b-d11344bb6a92/canvas/feccc0eb-d8d4-4196-8dfd-21ee38fe6af0 ]
Video Walkthrough: [https://youtu.be/lN5iBnjXkAw]
Project Description:
Most creators use generative AI to create isolated images or short videos. I wanted to push Melius to its absolute architectural limits by building a fully automated, scalable production pipeline designed to generate a cohesive 60-page noir graphic novel. I successfully rendered 18 complete pages (over 100 panels) end-to-end, but I eventually hit the hard limits of both the UI performance (severe lagging) and my credit balance. However, the engine architecture itself is fully functional, proven, and ready to scale. It is not just a comic; it is a workflow-native engine designed for continuous storytelling.
Process Overview & Architecture (What I Used):
To achieve absolute consistency without the system hallucinating or losing the plot, I structured the Melius canvas like a software backend, utilizing multiple node types:
Phase 1: The Master Brain (World Building LLM)
I started with a primary LLM node acting as the "Showrunner." Given a single seed sentence, it generated a comprehensive "Story Bible," locking in the overarching plot, environmental aesthetics, and strict character design rules.
Phase 2: The Logic Parsers (Workflow Routing LLMs)
To prevent data overload, the output from the Master Brain is fed into secondary, specialized AI Text Nodes. These act as logical routers. They parse the master script and isolate exact prompts for specific panels, ensuring each downstream image node receives only the precise data it needs.
Phase 3: The Render Array (Parallel Text-to-Image)
The parsed prompts are fed simultaneously into a battery of Image Generation nodes (Flux/Grok). This parallel array generates the raw pages (6 panels at a time) maintaining the high-contrast noir aesthetic dictated by the Master Brain.
Phase 4: The Cinematic Climax (Start/End Frame Video & Audio)
To fulfill the ">1 node type" requirement and add a massive "wow" factor, the final panels of key scenes are routed into Image-to-Video and Audio (ElevenLabs) nodes. By feeding Panel A (Start Frame) and Panel B (End Frame) into the video model, the engine creates hyper-smooth, logical cinematic transitions for the story's climax, complemented by epic sound design.
Extensiveness of Agent Use:
The Melius Agent was my co-architect throughout this build. I utilized the Agent to help design the logical flow of the parsing nodes. When dealing with the massive data flow from the Master LLM to the 6-panel Render Array, the Agent helped structure the prompt extraction logic, ensuring the "spaghetti wiring" remained functional and the data routed correctly to the visual generators.
Feedback on Experience Using Melius:
The Highlights & UI Experience:
This is arguably the first AI agent I've encountered capable of genuinely grasping complex, high-level structural requests. While I am highly accustomed to the deep technicality of complex node-based tools like ComfyUI, Melius offers a brilliant contrast: the visual canvas is incredibly clean and accessible. The ability to visually orchestrate AI collaboration is phenomenal.
Areas for Improvement (Stress-Test Feedback):
Because I pushed the platform to its limits with this massive pipeline, I found a few severe bottlenecks:
Credit Exhaustion from Deep R&D: My ultimate goal was to finalize the entire 60-page project to the highest possible polish, but I hit hard credit limitations after rendering 18 pages. I burned through a massive portion of my credits purely on R&D—extensively testing different model outputs, probing the Agent's comprehension limits, and figuring out exactly how far and how deep I could push the node architecture before it broke.
Performance & Batch Errors: The web app currently struggles under heavy production loads. By the time I reached 18 pages, I experienced choppy canvas navigation and frequent errors when queuing multiple generation batches.
Wiring Logic at Scale: In massive multi-node networks, the Agent occasionally lost track of correct connections. It would claim everything was wired perfectly, but upon explicit prompting to double-check its work, it would discover its own routing errors.
Pre-Run Cost Estimator: A massive UX improvement for power users would be implementing a built-in UI feature that analytically calculates the exact credit cost of the entire node tree before hitting "Generate," rather than relying on the Agent's estimates.
Custom LoRAs: Adding support for custom LoRAs would be the ultimate upgrade for maintaining absolute character consistency in sequential art pipelines like this one.
wow i didn't even know our agent was capable of this
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
portfolioreview
The best portfolios tell a story, not just show a grid. Share yours for feedback.
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?