Freelancers using Melius
Freelancers using Melius
Sign Up
Post a job
Sign Up
Log In
Filters
1
Projects
People
Révolté
pro
Milan, Italy
Brand identity, web design & dev. Fast, precise, opinionated
$5k+
Earned
12x
Hired
5.0
Rating
779
Followers
expert
Expert
Follow
Message
Brand identity, web design & dev. Fast, precise, opinionated
3
Helix Protocol Brand Identity for Bio-Futurism
3
32
0
OSMIUM Brand Identity & Product Design Project
0
21
2
LATRO°: The City, Annotated Brand System
2
27
0
TOKAN Brand Identity Design
0
23
Melius
(7)
Follow
Message
Denys Dod
pro
Lisbon, Portugal
Framer design and Motion for SaaS/AI products | Duvo Studio
$5k+
Earned
5x
Hired
5.0
Rating
103
Followers
Follow
Message
Framer design and Motion for SaaS/AI products | Duvo Studio
6
Audeo Framer Website Design and Development
6
72
2
Launch Video - amo (Fintech Product) Storyboard and Animation
1
2
8
3
Nodus — Brand System and Framer Dev for a Global Edge Network
1
3
17
5
Pitch Deck and Visual System ( AI Data Center )
5
21
Melius
(1)
Follow
Message
Shezaan Ansari
pro
Mumbai, India
AI Video Producer | Brand Designer
$10k+
Earned
18x
Hired
5.0
Rating
269
Followers
expert
Expert
+4
Follow
Message
AI Video Producer | Brand Designer
5
A cinematic exploration of scale, atmosphere, and survival.🏜️📽️ I wanted to see how far I could push Seedance 2.0 and GPT Image 2 by using them non-linearly. Instead of generating single clips, I used a Custom Text node to set a strict visual language, built a 2x2 storyboard sheet to guarantee asset control, and fed that entire structure into the video engine. The final cut features custom sound nodes to drive the narrative pacing from a quiet opening whisper to a massive industrial crescendo.
5
5
955
6
If your creative assets don't evoke a physical reaction, they fail. 🧠⚡ In CPG marketing, attention is the only currency that matters. If a user doesn't stop within the first 1.5 seconds, your render didn't happen. For this Fizzbears spot, my goal as a Creative Producer wasn't just to make something "look cool"—it was to trigger a sensory memory. I wanted to simulate the exact, mouth-watering feeling of biting into a sour gummy using style scale and hyper-vibrant color theory. The Attention-Stopping Stack: 💎 Crystalline sugar rendering that feels tangible. 🌌 An "Interstellar-style" light tunnel transition. ⚡ Audio design that snaps perfectly on the beat. Stop chasing generic loops. Start building worlds that command attention. 📌 Drop a comment or message me if you want to elevate your brand’s next visual campaign.
2
6
748
2
Hey Contra fam! 👋 A lot of you saw Version 1 of my Interstellar AI project when it won 2nd place in the CapCut Video Studio Challenge recently. The support from this community during that run was absolutely unreal, so I wanted to share the next evolution with you first. Here is Version 2. I wanted to see how far I could push the current AI video stack to mimic high-end cinematic language. I built this entirely from scratch—made in Higgsfield—to try and nail a very specific, gritty, and tactile aesthetic. Dialing in the prompt architecture to get consistent, heavy motion (like the massive wave and the curved space station) took a lot of trial and error, but the level of control Higgsfield offers creators right now is incredible. I’m always refining my prompt workflow for client projects, but passion pieces like this are where the real R&D happens. If anyone is currently building out their own AI video pipelines or wrestling with motion consistency, drop a comment! I’d love to chat about what tools you’re all testing right now.
2
2
200
1
When clients ask what the difference is between a generated video and a directed AI video, this is the benchmark. This project explores a high-end, cinematic visual language—specifically targeting a gritty aesthetic. The Workflow: Prompt Architecture: Built initial shot structures using custom Tapebot integration for precise, repeatable visual rules. Motion Generation: Orchestrated complex motion pipelines using Seedance and Nano Banana Pro, focusing on the physical impact of the subjects (like the heavy gallop of the horse) and subtle camera tracking. Sound Design: Grounded the generated visuals using isolated, ambient foley to build tension, proving that premium sound design is non-negotiable for AI content. Available now for AI Video Lead roles and creative motion projects. Let's build something cinematic.
1
219
Melius
(2)
Follow
Message
Sílvia Pinho
max
Lisbon, Portugal
I turn social strategy + UGC into *actual* revenue
$10k+
Earned
17x
Hired
5.0
Rating
370
Followers
Top
Expert
Follow
Message
I turn social strategy + UGC into *actual* revenue
5
As creative freelancers, our best work often finds itself buried in a desktop portfolio folder because we are simply too busy - or too tired - to do outreach and pitch ourselves (please tell me I'm not alone in this!) The Momentum Machine changes that. Built entirely on Melius, this interactive, multi-agent workspace takes your raw, messy project assets (images, videos, text, or analytics screenshots) and instantly transforms them into a compounding business development ecosystem. Instead of tackling projects individually, it builds a "snowball effect" where one client effortlessly generates the next. 🔗 Melius Project Link: https://app.melius.com/projects/8d06081b-be00-4f6d-9bb9-dff7d2fe9120/canvas/68c66aba-2fa1-48b9-a594-44bfd48c9c58 You can watch the video to see how it works in the backend and the thought process behind it, but essentially it goes like this: ⭐ The freelancer drops their project files (e.g., product photos, a text testimonial, or a cropped screenshot of analytics). ⭐ Node A uses advanced data extraction and OCR to scan the uploads, extracting any key metrics or features of your work. ⭐ Node B infers the creative style and outputs 5 to 10 complementary, non-competing industries that could be a good fit for you. ⭐ Node C weaves the raw data into a high-conversion marketing narrative structure: Hook ➔ Struggle ➔ Aha! Moment ➔ Hero Stat ➔ Closed Loop. ⭐ And then the final outputs: a case study, cold email pitch draft (to pitch those complementary industries we identified in node B), a Contra portfolio entry, and a video script to promote your work. PLUS a bonus Contra portfolio cover and a b-roll video in case you don't feel like being on camera for any reason. PS: building this on Melius was incredibly intuitive - my favorite feature by far being how the agents interact with you in chat during the creative build - instead of just giving a generic output, they prompted me with intelligent follow-up questions with multiple choice answers to fill in the strategic blanks. It genuinely feels like collaborating with a sharp creative partner rather than just using a tool.
5
471
4
hear me out: a Tinder...but for freelance jobs 🤔 idk about you but every morning i find myself sorting through a bajillion jobs in different platforms, looking for any red or green flags that make me want to apply or give up on freelancing all together. is it just me? so i came up with the idea for FILTER, your morning companion to swipe left and right on job cards with the key info you need to know about them, all while you sip your morning coffee ☕️ then, once you're fully awake and ready for the day, you open your laptop and there you have it: an email with the list of all your picks, so you can apply and move on with the rest of your work day! check it out for yourself (or see the walkthrough in the video below!) https://app.flowstep.ai/file?activeFileId=4ce93422-2008-4b60-9703-30561f1c02eb
4
158
45
oof! finally able to share the final piece!! if you haven't been keeping up with my updates: ⭐ on day 1 I brainstormed alongside Gemini, merging my ideas with theirs and ending up with an outline of what I wanted to do for this challenge ⭐ day 2 I collected the raw footage I filmed and started putting together a folder with all my assets ⭐ day 3 I dove into Envato for the first time in years and found stock video, music and sfx, and used AI to alter both one of my own clips and a stock one ⭐ day 4 was for the final touches, where I recorded the voiceover and put all the other assets together into the video you can see below - my final submission! (I also attached a screenshot of what my final project folder looked like - organized by source of each asset) my biggest AI win was definitely the clip where I asked it to replace my water bottle with the coffee machine and it mimicked my rings and tattoos without me even asking my AI flop, where I decided to intervene because AI just didn't do it justice, was the voiceover - it just felt off and emotionless, and instead of trying to tweak it to perfection I decided to just pick up the mic and do it myself! I'm also gonna be sharing this final video on my Instagram @freelancingwithsilvia - feel free to follow me there for all the freelancing vibes 🤩
12
45
3.1K
7
As a marketer and business owner, I know one thing: in 2026, if your business doesn't have both a website and at least one social platform, it feels a bit sus... 😒 That’s why for this challenge it took me less than a minute to choose my favorite local spot: Coffee Village, an eclectic, quirky coffee shop in Palmela that serves the most amazing cappuccinos and cheesecakes 🤤 But...despite their incredible charm and delicious treats, their online presence wasn't doing them justice - hence why I decided to give them the digital home they deserve ✨ 🟥 BEFORE BASE44 They had no website whatsoever, and their custom cake orders were completely scattered across a landline phone, Facebook messages, and Instagram DMs. Managing this during holiday rushes like Christmas and Easter must've been CRAZY 😵💫 🟩 AFTER BASE44 I built a fully responsive, bilingual (PT/EN) website that both reflects their unique decor - including their signature wall stripes and dark wood tables - and speaks directly to the audience they're trying to attract! You can see it for yourself 👉 https://coffeevillage.base44.app As for that cake order situation...that's where the automation came in! I built a streamlined cake order system, so customers can submit their orders in one centralized place. The backend workflow automatically: 👉 Triggers an instant email confirmation to the customer. 👉 Sends a structured email summary directly to the owner. I'm handing the site over to the owner tomorrow and can't wait to see their reaction!!! Next up on my to-do list? Bringing my professional camera to the shop to shoot even better photos and videos for them, both of the space and the food & drinks! Here's to helping local businesses glow! 🥂
3
7
480
Melius
(1)
Follow
Message
Bob Vasic
pro
Dublin, Ireland
AI SaaS Builder & Web3 Security Architect | Ship Fast
$1k+
Earned
2x
Hired
5.0
Rating
482
Followers
Expert
Follow
Message
AI SaaS Builder & Web3 Security Architect | Ship Fast
41
PROJECT NAME AION PYR — The Aitherioi PROJECT LINK https://app.melius.com/projects/029a5c7f-3a2a-4c7b-a24c-e25f36815d91/canvas/98b87dac-fcc4-411b-8695-83b7dc318726 CONCEPT / PROJECT DESCRIPTION AION PYR is a one-minute instrumental progressive-rock film by The Aitherioi, a fictional trio of pale pre-terrestrial beings older than Earth. They were here when the planet was born from heat, basalt, and lava, and they remain calm as that world dissolves into stardust. The film follows them performing inside a collapsing volcanic cathedral while lava, steam, lightning, and stone slowly give way to void. The music is built only from guitar, bass, and drums: slow, heavy, repetitive, bass-led, and cathartic. PROCESS I started by defining The Aitherioi: a fictional pre-terrestrial trio with a shared visual identity, pale ethereal bodies, severe faces, long dark hair, and calm expressions. Then I built the visual system around contrast: fossil-dark basalt, living lava, white steam, lightning, and their stillness inside collapse. I created character assets, face studies, wardrobe references, instrument references, environment plates, keyframes, and individual video scenes. The music was built first as a strict one-minute instrumental progressive-rock track using only guitar, bass, and drums. The video was then structured to follow the track: bass opening, wide trio, basalt corridor, guitar catharsis, drummer pulse, matter dissolution, and final void. Finally, I stitched the scenes together with clean cuts so the film follows the music without extra transitions or title cards. FEEDBACK ON BUILDING WITH MELIUS Melius worked best as a production canvas rather than a single-prompt generator. The node-based workflow made it possible to build the project in layers: character identity, environments, audio, keyframes, video clips, and final assembly. That helped keep the concept coherent while still allowing corrections when individual shots needed refinement. The biggest challenge was visual continuity, especially keeping The Aitherioi consistent across scenes. The most useful approach was creating strict reference assets first, then using them as anchors for keyframes and video generation.
18
41
2K
9
Challenge submission is in judges hands now. 🧠 https://on.contra.com/mJH8Qb (https://on.contra.com/mJH8Qb)This chalennge specifically was very personal to me, I would appreciate your like, comment and share, each like contibutes to my goal to make my music studio more famous and to reach out with the message to the world. On top of that, I have been building on Base44 for a year now, and became an official Partner, because @Base44 is my favourite building tool among competition, since its giving me full freedom regarding web development tech stack choosing, fine tuning of frameworks and libraries, frontier models and context preservation, and active Base44 community both on Discord and the platform itself. It would be nice to make it to top 3 at least and to give a surprise as an appreciation and grattitude to the Temple Lane Studios for giving us a retreat space for playing and enjoying our rock'n'roll music in this modern, fast paced world and way of living by just working hard 24/7 and somehow staying sane along the way. They wrote history, we are making it, for future generations to be able to take over after us. Take a look, hope you will enjoy the experience! Thank you to everyone for each like, share and support, it really means a lot ♥️
3
9
1.3K
20
OFFICIAL SUBMISSION — ECHOES OF TEMPLE LANE For the Base44 x Contra #GiveItAGlow Challenge, I chose a real Dublin business that has been part of my life since 2018: Temple Lane Studios and the Irish Rock ’n’ Roll Museum Experience. This was not a random business choice. Temple Lane has been my place to rehearse, reset, disconnect from everything else, and play proper fat rock ’n’ roll with the band. BEFORE The museum already had a strong identity and an established website for presenting its history, exhibitions, tours and visitor information. The opportunity was not to replace that foundation, but to explore an entirely new digital layer: one that could translate the atmosphere, memories and emotional character of the physical building into an experience people could enter. AFTER I built Echoes of Temple Lane — a live, publicly accessible Base44 experience designed as a cinematic digital exhibition. Visitors move through atmospheric memory rooms, recovered photographs, archival records, rehearsal spaces, personal performance moments and historical fragments. The journey includes the Room of Celebration, the Room of Punk, interactive archive elements and a final narrative sequence called The Last Echo. This is not a static redesign. It is an experience built around motion, sound, discovery and memory. AUTOMATION Visitors can submit their own Temple Lane memory through the exhibition. The memory_scribe AI agent helps shape each contribution into a guestbook-ready draft. The caretaker agent supports the exhibition experience, while the Caretaker Memory Digest workflow runs every three hours, gathers new visitor memories, prepares a moderated report and emails the guestbook digest for review. The workflow has been tested end-to-end with a real submission, and the attached dashboard proof shows the completed automation run. BUSINESS VALUE The system creates the foundation for a moderated, community-generated archive while reducing the manual work required to collect, organize and review visitor stories. The walkthrough video focuses on the immersive visitor experience. The attached screenshots document the complete transformation: — the original online presence — the finished Base44 experience — the AI agents — the scheduled automation — the successful workflow run — my genuine connection to Temple Lane Studios since 2018 Live experience: https://temple-lane-studios.base44.app Original website: https://irishrocknrollmuseum.com/ (https://irishrocknrollmuseum.com/)LinkedIn post: https://www.linkedin.com/posts/bobvasic_giveitaglow-giveitaglow-base44-ugcPost-7482178973616119808-rd78 (https://www.linkedin.com/posts/bobvasic_giveitaglow-giveitaglow-base44-ugcPost-7482178973616119808-rd78/?utm_source=social_share_send&utm_medium=member_desktop_web&rcm=ACoAAAWbOcYBym9kgZZll4IyyFfT9tR-b1MMg5U)X post: https://x.com/RaptorLabsX/status/2076413890817400843?s=20 Built independently with @Base44 for the #GiveItAGlow Challenge. From a traditional museum website to a living digital archive. #Base44 #Contra #TempleLane #IrishRockNRollMuseum #Dublin #DigitalMuseum #InteractiveDesign #Automation #AI #BuildInPublic
4
20
1.4K
20
NULL is a complete mascot system built for a fictional cybersecurity company, proving that a single character can remain instantly recognizable across branding, posters, merchandise, social campaigns, motion, and environmental storytelling. The project explores how strong character design becomes a cohesive brand by combining identity, world-building, and consistent visual language into one unified ecosystem. NULL is the quiet guardian of /dev/null, the hidden place where corrupted code and dangerous software disappear forever. Calm, observant, and endlessly patient, NULL finds vulnerabilities before attackers can exploit them, protecting developers without ever seeking attention. Rather than fighting threats with force, NULL simply ensures they quietly cease to exist. Every application in this project expands that idea while preserving the same recognizable identity. Project: https://www.recraft.ai/project/b49a3f35-5c69-43f6-8da1-f293bc7d618f (https://www.recraft.ai/project/b49a3f35-5c69-43f6-8da1-f293bc7d618f)@Recraft x @Contra
3
20
1.5K
Melius
(1)
Follow
Message
Kris Anfalova
pro
Warsaw, Poland
Premium UI/UX & Web Design for Fintech, SaaS & Web3 | Framer
$10k+
Earned
1x
Hired
5.0
Rating
224
Followers
expert
expert
+1
Follow
Message
Premium UI/UX & Web Design for Fintech, SaaS & Web3 | Framer
1
The Smart Shoulder Drone for Motorcycle Passengers After over 100,000 kilometers traveling as a passenger on a heavy Harley-Davidson, I desperately wanted a way to capture the journey without sacrificing safety or the sheer joy of the ride. Holding a phone or a heavy camera at highway speeds is dangerous and exhausting. It’s a compact, magnetic shoulder-mounted drone controlled by a smart leather glove with an embedded micro-OLED screen. My Melius Workflow: I utilized the Melius agent not just to prompt, but to architect a complete production studio on the canvas. Stage 1: Hardware Lock (The Source of Truth). I briefed the agent to generate studio-quality master shots of the drone and the smart glove. I then instructed the agent to hard-wire these specific nodes as global visual references (Image-to-Image/ControlNet) for the rest of the canvas to prevent the model from hallucinating new designs. Stage 2: Storyboarding. The agent built a storyboard branch, placing the locked product designs into realistic environments (highway, golden hour) using precise text nodes to establish the narrative. Stage 3 & 4: Commercial & UGC Video Pipelines. I tasked the agent to build complex Image-to-Video branches. For the promo video, the agent generated sequential keyframes (First, Mid, Last) showing UI interactions and mechanical sliding, which were then routed into video nodes. For the UGC branch, the agent completely shifted the aesthetic to raw, vertical smartphone footage while maintaining the exact hardware design. Stage 5: Assembly. Text nodes were used as a director's script on the canvas to dictate the exact sound design and features (USPs) being highlighted before final video generation. Feedback: As a UI/UX designer, the node-based canvas feels incredibly intuitive. Generative AI usually feels like a chaotic slot machine, but Melius turns it into a structured, production-ready pipeline. The ability to converse with the agent, ask it to build branches based on specific logic, and literally see the "wires" connecting a master reference to a final video output gives an unprecedented level of creative control. It allowed me to act as an Art Director rather than just a prompt engineer. Project flow: https://app.melius.com/projects/b3edd6cc-ec50-49fa-b861-80fbe443ef97/canvas/2aefaa54-3d08-4265-b21b-83233c694be2 X Post: https://x.com/KrisAnfalova/status/2056718110682489214?s=20 Travel more and ride safely!
1
857
11
Designed the landing page UI for Agent OS — a next-generation AI platform that helps art directors, designers, and studios streamline their generative workflows. B2B AI tools often fall into the same trap — they look like overly complex, highly technical dashboards. The goal was to build an interface that actually appeals to creative professionals, balancing advanced AI capabilities with a premium, highly aesthetic visual language. An editorial art direction that blends modern sans-serif fonts with elegant serif italics, paired with striking, organic floral visuals. I used a glassmorphic chat overlay to showcase the AI's prompt-to-image generation feature directly in context. It proves that generative tools can feel deeply human, inspiring, and beautiful rather than purely functional. What's in the interface: — Contextual glassmorphic chat overlay — High-contrast editorial typography system — Seamless blend of organic photography and precise UI elements — Clean, conversion-optimized top navigation The process: — Midjourney: Generated the vivid, high-fashion floral photography and campaign assets. — Jitter:Crafted the smooth UI motion and interactions for the floating chat interface. — Figma: Designed the entire layout, typography, and UI system. A case in making artificial intelligence feel like a creative partner, not just a software tool.
5
11
99
21
Vestris — from ratified contract to closing-ready, on autopilot Just wrapped one-week sprint designing the landing page for Vestris, a YC S26 startup automating mortgage title & closing work. Sharing the process because a few things about it were genuinely different from a typical SaaS landing page project. The brief Vestris automates the unglamorous middle of a real estate closing — chasing documents, prorating taxes, drafting closing disclosures, coordinating between lender/agents/title company. The founder wanted the site to feel "homey," not like enterprise software — because the buyers here are mom-and-pop title companies, not enterprise IT departments. Process 2 hero concepts tested in parallel (a quieter parenthetical headline vs. a bold full-width one), each with copy variants, sent as a single comparison sheet rather than one "final" direction — let the founder react to real trade-offs instead of guessing what I meant. Redesigned the site's core interactive block — an 11-step "how it works" breakdown — three separate times based on live feedback: first a desktop accordion, then a mobile-specific pass (accordions don't compress well under ~380px), then a full restructure into a 2×2 grid after the client flagged the original zig-zag layout for being "repetitive and too long to scroll." The illustrated hero background (watercolor countryside, cottage) needed to dissolve into the brand's cream background at the edges — but a standard blur/gradient looked flat next to the painterly art style. Built a small custom tool (canvas + JS) that applies ordered Bayer dithering to fade the illustration into the background color pixel-by-pixel instead of blending — it reads as grain, not gradient, and matches the hand-painted texture instead of fighting it. Turned it into a reusable tool with adjustable fade area, blur radius, dot size, and a transparent-overlay export, so it's not a one-off script. Figma for design, Framer for the build, custom canvas/JS tooling for the image-edge treatment, Midjourney for the base illustrations. vestris.ai (http://vestris.ai) — live now.
10
21
405
78
Finally get to share this one — been sitting on it for a while and couldn't post until now 🎉 Designed the full landing page (and a bunch of product screens) for XRS, a prop trading platform. The idea: traders pass a funded-account challenge, trade the firm's capital, and keep up to 80% of the profits. Prop trading is a pretty saturated space and most platforms look the same — dark UI, generic trading stock imagery, nothing that actually sticks. So instead of the usual playbook, I leaned into a black-and-gold identity — including custom, hand-crafted illustrations built specifically for this project (the glowing spheres, gradient icons, all of it) instead of stock assets or generic 3D packs. Some of what's in there: — Custom illustrated icons for the 3-rule system and "trader to fund manager" journey — Floating reward/payout cards as social proof right in the hero — A plan selector so people can pick account size, currency, challenge type — Trustpilot ratings + a testimonial section for trust — Support + FAQ blocks, because people are putting real money on the line Genuinely proud of how this one came together — every visual element built from scratch for the brand, full case + more screens are up now, finally 👀
29
78
3.3K
Melius
(1)
Follow
Message
Stas Tatarinov
pro
Los Angeles, USA
AI Image & Video Producer | AI Ads | AI UGC
$10k+
Earned
6x
Hired
5.0
Rating
272
Followers
Top
Follow
Message
AI Image & Video Producer | AI Ads | AI UGC
53
I made up an energy drink brand and created ads, photoshoot, and merch for it using Melius🚀 Jovi is a concept brand energy drink made with real juice inside. Active, modern, yet simple. For anyone that wants to be a part of it. Comes with four flavors. I illustrated the sketches of each bottle and fed them into Melius to begin with, the rest is history. Video includes the process of how I generated all the assets. Using Melius was easy and great experience for someone who is into making node based AI image & video content with extra help! Project link: https://app.melius.com/projects/6d1b8b5d-21ac-47a8-9f12-414de83ca128/canvas/678a9172-5d47-4f6a-88cb-2ccbc916cdcb
13
53
1.7K
31
Excited to enter Another Big Ad Contest hosted by Runway for a chance at $100,000 in prizes!🔥 My pick was a portable speaker Jaunt as my product. All the visuals were generated inside Runway. Song was generated by me in Suno. Post-edit in DaVinci Studio. Let me know your thoughts!
7
31
1.2K
69
For my #EnvatoChallenge I made a social reel called People. Every stranger you pass is living a life as full and complicated as your own. You just never get to see it. That was the whole starting point. You catch a half-second of someone and your brain files them as an extra in your movie, while they're the main character of theirs, with a whole thing going on you'll never know about. So I tried to make something that sits in that feeling. No story line, but just a reminder that everyone's got one. I used Envato for music, images and videos starting with stock images that I got inspired by and used as references and to expand ideas from those. I believe the main human by design call I had to make was not only the final edit, but prompting for "imperfect" generations. AI is trained to give the perfect image every time, centered angles, equal proportions, bright colors. I tried the complete opposite while still trying to make it look like a complete social reel.
26
69
6.1K
77
My submission for #RenoiseChallenge is a commercial for Veil. The goal was to make something cinematic with a twist at the end. Tools used in Renoise: Midjourney, GPT 2, Kling 3.0, Seedance 2.0. Post-edit in DaVinci Resolve. Unfortunately couldn't figure out a way to share my canvas workflow, but check out the screenshot in the comments below. Let me know your thoughts🧠
35
77
4.1K
Melius
(1)
Follow
Message
Jelena Stricak
pro
Zagreb, Croatia
AI-Native Builder | Apps, Templates & Websites Shipped Fast
1x
Hired
5.0
Rating
269
Followers
Expert
Follow
Message
AI-Native Builder | Apps, Templates & Websites Shipped Fast
37
The Painter of Cities is a Melius-built cinematic short about an impossible gilded automaton that paints a living city onto a monumental black wall. From the city he creates, a female droid briefly appears within the painted surface. They reach toward each other, almost touching, before she is reclaimed by the wall. It is a quiet story about creation, longing, and the tragedy of making something beautiful that cannot fully enter your world. https://app.melius.com/projects/23546fb0-e3a3-4074-925f-676dfe384aad/canvas/f96fdb6f-cf03-40cd-ba59-f1ddd40a23a6 PROCESS STEPS The project began with the challenge theme: create something that should exist, but doesn’t. The core concept became The Painter of Cities: an impossible gilded automaton that paints a living city onto a monumental black wall. Melius was used to generate sequential image keyframes for the story: the city being painted, the female droid appearing inside the wall, their near-touch, and her return to the painted surface. The prompts were refined through several iterations to preserve visual continuity across the male droid, female droid, city wall, studio, palette, and old-master oil-paint aesthetic. Short silent video scenes were generated from the keyframes, then adjusted to control pacing, motion, transitions, and emotional tone. The video scenes were stitched into a final silent film. An original instrumental music cue was generated to match the final timing and emotional arc of the film. FEEDBACK ON USING MELIUS Melius worked best as a visual production canvas rather than a one-shot generator. The node-based workflow made it possible to build the project step by step: image keyframes, video scenes, stitching, music, and final assets.The strongest part was being able to iterate visually and preserve the creative process inside the canvas.The hardest part was controlling motion continuity between generated video clips. Some transitions and character movements required very precise prompting, especially when preserving the same droid designs and painterly world across multiple nodes.
33
37
1.8K
2
Hot afternoon, low stakes, and a little pop-art experimentation. I animated this portrait grid with subtle, different micro-expressions in each frame—just for the fun of seeing how much personality can live in a few seconds of motion.
2
90
9
Teachers spend hours planning. I built something to give that time back. AI Lesson Forge is live 🎓 Describe what you want to teach — get a full lesson plan, quiz, worksheet, rubric, or homework in seconds. Organize everything into projects, plan your week on a visual calendar, share read-only links with your team, and export to PDF or your calendar. Built for real classrooms: standards-aligned, editable, and yours to tweak. Less paperwork. More teaching. Try it → https://ai-lessons.base44.app
4
9
394
5
It's been a year and Solmint's growing stronger every day! I am so proud to be a part of this project since the beginning. Create your token in a moment, solmint.dev (https://solmint.dev)
5
108
Melius
(1)
Follow
Message
Explore people