
Dinda Prasetyo
@heydin_ai • 6,269 subscribers
AI Filmmaker | @adobe Ambassador | Partners: Runway, Kling, Hailuo, Freepik, Capcut, Pixverse, Pika, TopazLab, Openart, Dreamina | [email protected]
Shorts
Videos

Seedance 2.0 kinda makes it hard for agencies and production houses to ignore AI now.
Dinda Prasetyo298,595 Aufrufe • vor 3 Monaten

Everyone’s talking about how powerful AI is… but honestly? Power means nothing without control. AI can be fast, cinematic, unpredictable, even wild. That’s why control changes everything. In this content, I’m sharing how I control AI generative image and video shots using Adobe Firefly and Adobe Photoshop powered by partner models like Nano Banana Pro. Instead of just generating and hoping for the best, I shape the composition, refine details, lock consistency, and iterate directly inside the Adobe ecosystem. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels
Dinda Prasetyo263,685 Aufrufe • vor 3 Monaten

This is our second head-to-head test between Kling 3.0 and Seedance 2.0. This time, we pushed both models further, including dialogue-driven Sci-fi comedy shots and even a singing scene. Every single shot was generated using: • The exact same base image • The exact same prompt • No re-generate • No second attempt • No prompt refinements. What you see is the pure first output from each model under identical conditions. So… which one performs better? Seedance 2.0 generated by Ilham Setyawan on BytePlus
Dinda Prasetyo196,189 Aufrufe • vor 3 Monaten

I’ve always been a huge anime fan, especially Chainsaw Man. So I wanted to push my limits a bit and try creating a live-action version of Denji vs. Katana Man. Since anime fight scenes are known for their insane speed and intensity, translating that energy into live action became a challenge I genuinely enjoyed. This whole sequence was built using an image-to-video workflow with Hailuo AI (MiniMax) 02 and Kling AI 2.5 Turbo, with the base images from Nano Banana Pro on Freepik (now Magnific) . Edited in CapCut Pro and upscaled with Topaz Labs for that final punch. Such a wild experiment, but honestly super fun to make. What do you think about the result?
Dinda Prasetyo210,588 Aufrufe • vor 6 Monaten

I just created this video using only one base image and one audio input, using the omni-reference feature in Dreamina AI This honestly feels like a game changer, we can finally produce K-pop style music videos much more easily. Even with realistic facial features, the audio integration stays smooth and natural. So far, I haven’t seen any other video model handle camera movement and hyper-detailed direction through prompting quite like Dreamina Seedance 2.0. What do you think? #DreaminaSeedance2 #DreaminaAI #DreaminaCPP #Seedance2 #seedream5lite
Dinda Prasetyo64,133 Aufrufe • vor 2 Monaten

SKYLAND | AI Short Film Fantasy Skyland is an AI-powered fantasy short film that takes you on a breathtaking journey with Aeryn Solveth and his loyal flying fish. From soaring above the futuristic city of Cybryne to returning to his homeland of Eryndor, Aeryn’s adventure is filled with wonder, imagination, and magical encounters. Skyland isn’t just a story. it’s a cinematic exploration of a world where skies are alive and every horizon promises something new. Tools Used: Board & Script made with Adobe Firefly Base Image Midjourney v7 Nano Banana Google Gemini Flash 2.5 in Adobe Firefly Video Luma Ray 3 in Adobe FIrefly Image Retouch Adobe Photoshop Sound Effects VO Sequence CapCut This film was created to take part in the AI short film competition at Chroma Awards
Dinda Prasetyo206,606 Aufrufe • vor 8 Monaten

Hollywood-level drama is now literally in your hands. Testing Kling Voice Control with Kling AI 2.6 (Native Audio), and I’m genuinely impressed. This feature allows custom voices, while the voice generation still follows the prompt logic, making consistent character voices across scenes finally possible. That’s a huge leap for cinematic storytelling. Workflow breakdown: Base image Midjourney Character development → Nano Banana Pro, using a 3×3 grid for faster iteration Video → Kling 2.6 with Native Audio + Voice Control What do you think, does this already feel Hollywood-ready to you? 🎬👀
Dinda Prasetyo104,485 Aufrufe • vor 5 Monaten

Now anyone can become a filmmaker. 🎬 In this video, I’m sharing my concept-to-creation workflow for making a short film using Adobe Firefly , from prompt-based video edits to sequencing everything inside the new Adobe Firefly Video Editor. One of my favorite parts is how easy it is to refine clips with text prompts, explore variations, and turn ideas into finished videos without switching tools. It really speeds up production from rough cut to final output. #AdobeFireflyAmbassadors #Ad #ConceptToCreation
Dinda Prasetyo67,851 Aufrufe • vor 4 Monaten

NEXII - Self Made | Kpop Style AI Music Video This experimental music video inspired by kpop, made 100% with AI. Base images: Midjourney v8 Video: Dreamina AI Seedance 2.0 Edit: CapCut Music: Suno V5.5 4K version in the comments below 👇 #DreaminaSeedance2 #DreaminaAI #DreaminaCPP #Seedance2 #seedream5lite
Dinda Prasetyo32,670 Aufrufe • vor 2 Monaten

WOUNDS | AI Short Film In this short film WOUNDS, I wanted to see how far Kling AI 3.0 could really deliver raw human emotion. I pushed it hard, silence, tears, shaky moments, broken voices. And honestly… I’m kind of amazed by how much emotion it managed to hold in these shots. Now I’m curious, did you feel it too? Did the emotion come through for you while watching this scene? Tools used: Video Kling 3.0 Image Nano Banana Pro Adobe Firefly Image retouch Adobe Photoshop Editing Adobe Video Premiere 2026
Dinda Prasetyo52,199 Aufrufe • vor 3 Monaten

Kair Powered by Adobe AdobeFirefly Editing AdobeVideo Premiere Pro Image Retouch Adobe Photoshop
Dinda Prasetyo54,987 Aufrufe • vor 4 Monaten

FIRST TEST Seedance 2.0! From my initial tests, this is one of the more impressive AI video models I’ve tried so far. Dynamic motion feels fluid, prompt adherence is solid, and the efficiency really stood out, very little iteration needed. Everything you see here was generated using just one reference image + one prompt. I also tested a 3×3 image grid with no prompt at all, and the results stayed surprisingly consistent. Another highlight: sound design is already included, and it actually works really well. Tested via BytePlus 👉 More detail and access link to try Seedance 2.0 is in the comments.
Dinda Prasetyo45,450 Aufrufe • vor 3 Monaten

What if an entire AI Short Film could be born from just one single image? This AI short film, LEGACY, was crafted through an image-to-video pipeline with Kling 2.5 Turbo, transforming a single MidJourney frame into a cinematic experience. Tools used: Base image Midjourney , Nano Banana on Adobe Firefly, Kling AI 2.5 Turbo, Seedream 4 on Freepik VO & SFX ElevenLabs , Editing CapCut This film was created to take part in the AI short film competition at Chroma Awards
Dinda Prasetyo72,340 Aufrufe • vor 8 Monaten

K-pop aesthetic meets futuristic warrior vibes! 🖤✨ I’ve been experimenting with a cinematic K-pop look lately, and the results are blowing my mind. I started by generating the base characters in Grok Imagine and Midjourney, then blended them using Nano Banana Pro into a single still image to achieve the perfect mix of idol styling and tactical armor.. From there, I used Dreamina AI Seedance 2.0 to animate the choreography, upscaled with Topaz Labs for that 4K finish, and tied the whole mood together with some custom color grading in Adobe Video Premiere. In this clip, you see a fierce group of dancers performing in a dark, post-apocalyptic landscape. The sharp movements and high-tech outfits create such a powerful, otherworldly atmosphere. This kind of style is perfect for a futuristic music video concept, a sci-fi movie teaser, or a high-end social media ad. #DreaminaSeedance2 #DreaminaAI #DreaminaCPP #Seedance2 #seedream5lite
Dinda Prasetyo22,401 Aufrufe • vor 2 Monaten

Can we call this AI directing? 😂 Seedance 2.0 with the Omni Reference feature honestly feels like a total game changer. Summer Trip is one of my film which I made used Omni Reference, not only start frame anymore and for the first time, it genuinely feels like I’m directing the AI instead of just prompting it. The reasoning in Seedance 2.0 is seriously impressive. It understands intent in a way that feels collaborative. Of course, in production it still needs proper touch-ups in post, grading, timing, polishing details, but the foundation it gives is strong. Like it or not, we’re already here. And to be honest, my workflow has to evolve too. I can’t approach this the same way I did before. It’s less about generating random shots and more about guiding, refining, and thinking like a director from the start. Personally, I see this as a shift, not replacing filmmaking, but reshaping the role of the filmmaker. Now the question isn’t “Can AI make it?” but “How well can you direct it?”
Dinda Prasetyo29,385 Aufrufe • vor 3 Monaten








