Sharath Dasari

Filmmaker, writer, creative technologist at art & science's greatest convergence—I'm here to play my part! I Learn, create & share my art, insights & systems.

[Sharath Dasari @SharathDse]

Welcome to my creative universe!🔮

✨ Craft: Storytelling & Screenwriting

🤖 Tech: AI Creation

🎬 Process: Filmmaking

🧠 Why: Human Truth

Follow if you're curious + let's build it together. 🚀

[J.B. @VibeMarketer_]

https://t.co/5N53IsQ4UB

[Josh Daws @JoshDaws]

Claude Fable just built this entire product from one prompt. I'm blown away.

Shotblock is a 3D shot-planning tool for AI filmmakers — real lens math, actor blocking, 180 ° rule warnings, animatics, storyboard + prompt export. It researched storyboard conventions, wrote its own test suite, verified everything in a browser, and deployed it.

Then I asked for a promo video. It scripted, recorded, and edited the one below with minimal direction.

Give it a try. Free, no signup. Feedback button in the app for any issues or feature requests.

https://t.co/EEx9ClAC9m

[PJ Ace @PJaccetturo]

Ladies and gentlemen, it’s here:

I’m proud to announce that 'Nexus' will be my upcoming hybrid feature film.

Here is a 5-minute teaser, made by 3 people in 2 weeks.

Made with Dreamina AI using Octo & Dreamina Seedance 2.0, full workflow coming soon

[Google Flow @FlowbyGoogle]

https://t.co/qIJLqVs5pH

[patrick. @imPatrickT]

this is what real filmmaking looks like and nothing will ever replace it

[Min Choi @minchoi]

Gemini Omni is insanely impressive.

People are unlocking new creative ways to use it.

10 wild examples:

[MayorkingAI @MayorKingAI]

Seedance 2.0

Prompt:

[CINEMATIC SETUP]
Premium hand-painted 3D animation, semi-realistic stylized design, painterly realism, visible brushstrokes, epic steampunk chase, fast cinematic motion.

[CHARACTERS]
Kael Veyron: teenage boy riding a dark hoverboard with a glowing blue core.
3 Aether Sentinels: brass winged robots with glowing blue eyes and blue pulse gauntlets.

[LOCATION]
A vast vertical steampunk sky city at night.

[TIMELINE]
[0:00–2.5] Overhead drift — Kael stands on a rooftop rail, tense, as 3 Sentinels rise through steam behind him.
[2.5–4.5] Push-in — Black Breeze ignites in a bright blue burst, Kael leans forward and launches.
[4.5–7] Side tracking — Kael races across a sky bridge while the Sentinels chase close behind, firing blue pulse blasts that hit metal and throw sparks.
[7–9.5] Handheld follow — Kael jumps a huge rooftop gap as a pulse blast explodes behind him, filling the skyline with fire and smoke.
[9.5–12] Low tracking — Kael speeds through a tight pipe corridor, ducks debris, and skims under a rail arch as one Sentinel dives in close above him.
[12–15] Crane pull-back — Kael hits a rising ramp and bursts into the open sky above the city as explosions bloom below and the Sentinels fall behind.

[QUALITY ANCHOR]
4K, sharp clarity, visible brushstrokes, stable design, smooth motion, readable action, no flicker, no deformation.

[Hacknaut @Hacknaut]

One prompt. Zero edits. Full cinematic output. Seedance 2.0 on Higgsfield delivers:
→ Native 1080p motion
→ Realistic physics and lighting
→ Cinematic camera moves out of the box

[Framer 🇱🇹 @Framer_X]

Seedance has a hidden feature that feels illegal.

It lets you create old-school anime at lightning speed.

It’s called “in-between” - and it actually delivers.

Try it yourself 👇

[Abel Art @A_B_E_L_A_R_T]

An Artist | Short Movie

It’s been a while since I wanted to try SD2 with an animation style.
So I wrote a little story and made it along the way.

Made with @runwayml & @dreamina_ai

[Rian Doris @RianSweetDoris]

https://t.co/ExM0nOlBwr

[Prajwal Tomar @PrajwalTomar_]

I still don't think people understand what just happened with Claude Design.

Claude Design can now take you from rough idea to fully responsive, high-fidelity website design in 10 minutes.

Most builders are skipping Steps 1-3 and blaming the tool when results look generic.

This 4-step workflow gets you professional designs on the first pass:

(full breakdown in the article)

[Garry Tan @garrytan]

My simple secret to agentic coding

https://t.co/MvhHazLwf2

[Min Choi @minchoi]

Less than 34 hours ago, Google dropped Gemini Omni.

Minds are blown. And people are already coming up with wild use cases.

10 examples:

[Vadim @VadimStrizheus]

https://t.co/Nmh9l0tVtB

[Kōda @aimikoda]

GPT Image 2 - Original Character Generator Prompt

Got tired of seeing the same faces, the same outfits and the same “AI character” look everywhere, so I made a character generator prompt.

It’s designed to adapt to different styles and visual mediums. It’s variable-based.

You only need to fill 4 variables:

[CHARACTER SEED]
[AGE / BODY TYPE]
[STYLE]
[VISUAL MEDIUM]

Everything else is invented automatically.

It also includes originality + authenticity rules to reduce repeated AI faces, generic designs and accidental IP similarities.

Dropping example variables, more examples and the full prompt below ↓

[Viktor Oddy @viktoroddy]

Kimi K2.6 is actually a beast for design.

❤️‍🔥 Just recorded a tutorial on how to use Kimi K2.6 + to build award-winning $10k websites (step-by-step).

[Fokki @0x_fokki]

https://t.co/kdLiApx5H2

[Heather Cooper @HBCoop_]

Still kind of wild that I can go from a single character image → visual production graph → animated cinematic sequence in minutes.

A workflow that would've normally taken a day or multiple days to concept, storyboard, and visualize can now be explored almost instantly.

Using GPT Image 2 for the production graph + Seedance 2.0 on @runwayml for the video output variations:

[MayorkingAI @MayorKingAI]

I created a hand-painted 3D prompt inspired by a style similar to Arcane from the Netflix series using GPT Image 2 inside Leonardo

Prompts below 👇