Pinned Tweet
This is my entry for Arca Giden 2026. The base is Photography from roughly 15 years of my life brought to life with LTX 2 and ComfyUI with a bit of flux 2 for some of the elements and Foundation 1 for the audio stems.
We just raised $30M at a $500M valuation, bringing our total funding to $47M.
Led by @craft_ventures , with @PaceCap , @chemistry , TruArrow, and others.
But before anything else: this belongs to the community.
ComfyUI started as one developer and one open-source repo. No roadmap. No company. Just creators who wanted real control over how they built with AI.
That community is now:
→ 4 million users
→ 60,000+ community-built nodes
→ 150,000+ daily downloads
Every number traces back to people who built in the open, for anyone to use.
Here's where the funding goes:
→ Comfy Cloud: for teams and studios that need security and scale
→ Collaborative workflows: versioning and iteration built for how studios actually work
→ A better local experience: more seamless, more stable
→ Ecosystem reliability: making 60,000+ community nodes more dependable
→ Day-one model support: every major release, compatible at launch
We are not building a walled garden.
We are building open infrastructure, built to last.
Thank you genuinely,
The ComfyUI Team
J P retweeted
What a short-sighted take. We're entering an era of unprecedented creative empowerment where it's no longer about getting "picked".
J P retweeted
MetaPuppet’s new short film, Kyra, is a vibrant tribute to the New York artists who shaped his early creative journey.
From the graffiti writers who turned 5 Pointz into a living canvas to the subway drummers who transformed the city’s underground into a stage, Kyra celebrates the rhythm, color, and spirit that define artistic expression in its rawest form.
@MetaPuppet's short was created with @AdobeFirefly and debuted at @Adobe MAX.
🎥 Watch Kyra below.
J P retweeted
One of the most beautiful shorts I've seen. Love this
🌊 My short film NAGORI — Shadows Linger premiered this week at #AdobeMAX.
Told as a 2D Japanese folktale, it’s a poetic journey through ink-painted landscapes — inspired by my own experience as a father and filmmaker.
Created entirely inside @AdobeFirefly , produced at @promise
J P retweeted
Sharing my latest short, My Friend, Zeph, which premiered this week at #AdobeMAX.
I wanted to create a personal story about growing up — and what it means to hold onto wonder as we move between childhood and adulthood. As a dad to a young daughter, that theme really resonated with me.
To bring it to life, I used a hybrid approach that blended traditional filmmaking with generative tools within @AdobeFirefly. We shot with actors on location and against blue screen, then used AI to expand the world, enhance emotion, and visualize memory in a way that feels both real and dreamlike.
It’s been incredible seeing how these new tools can help tell stories that feel deeply human.
#AdobeMAX2025 #CreateWithFirefly
J P retweeted
Still buzzing from our @Techweek_ by @a16z event! ⚡️
Big thanks to everyone who came out, and to Albert Cheng from Amazon MGM for an incredible conversation with @gstrompolos about how AI is shaping the future of creativity.
The ideas, the energy, the people...what a night!
J P retweeted
Promise is building bridges to Hollywood, not walls.
As @gstrompolos shared at a16z's @speedrun event, our goal is to tell stories that couldn’t be made before in collaboration with the industry.
In venture, you back pirates 🏴☠️or stewards⚓️
@speedrun, I talked w/ @gstrompolos—architect of YouTube’s creator program & @FullscreenNet’s $845M exit - on moving from pirate to steward w/ @promise_ai to arm Hollywood’s next chapter. ⚔️ Raid the frontier or steward the empire?
J P retweeted
Nano Banana was the preview of Google’s new Gemini 2.5 Flash Image model. 🍌
I was given early access on @googleaistudio and created this video based off of 1️⃣ image
I was really impressed by how it maintained consistency on the character as well as small details. (Pay attention to his shirt and hat in particular.) 👀
Starting image is in the first comment 👇
J P retweeted
Have an idea? Bring it to life…
🔥What a time to be alive. This is 'Mind Tunnels.'
Made entirely with Gen AI.
To highlight a few tools:
☑️ Character Voices: The New ElevenLabs v3 Alpha
☑️ Script: Me + ChatGPT
☑️ Images: Midjourney v7
☑️ Video: Kling 2.1 Master, Veo 3, Higgsfield
☑️ Lip Sync: Heygen Avatar IV
☑️ Upscale: Magnific and TopazLabs
☑️ Editing: Adobe Premiere Pro
I locked down this weekend and explored one of my most cherished ideas about a future technology known as "Mind Tunnels" that allows a future race to send back data into the past, but not without consequences.
If you have been following me for years, I have explored this concept since the early Gen AI days. It's time to tell your big original stories.
Welcome to the new era of filmmaking!
J P retweeted
Yes it does… 👇
“This feels like indie filmmaking again—except with better tools and more ownership.” @gstrompolos
forbes.com/sites/charliefink…
J P retweeted
Featured in our AI Film Gallery: “Instinct” by Marcello Costa
What does it actually mean to evolve?
“Instinct” is a thought-provoking short film that follows a Neanderthal through a strange and surreal transformation in the jungle. It’s smart, layered, and leaves you wondering — is civilization really progress, or just another trap?
Head to curiousrefuge.com to watch more featured films or submit your own!
J P retweeted
Google approached me and asked if I would be down to collab with their research team to create a film for Google I/O. Not only would I have access to Flow, their latest AI filmmaking tool, but I would also be responsible for giving feedback on the product itself. The filmmaker in me was excited for the challenge, but the technologist in me was living out my dream in helping mold a next-generation product for a new era of filmmaking.
Experimenting with the tool has been a fun ride. Flow is built on @Google Deepmind’s most advanced models - Veo, Imagen, and Gemini, and has allowed me to world-build and create characters I have had in my head for years. I can create consistent characters, scenes, and stories with the ability to reference key ingredients. With Flow, it finally feels like filmmakers are in control. We can iterate freely and actually steer the ship in our creations.
I decided to create my short film “Freelancers” using Flow: An action-packed ride following two estranged adopted brothers—one methodical, the other loud and brash—who reminisce on their careers as international hitmen during dinner, until they realize they’ve both been contracted to carry out the same job.
@GoogleLabs
#EarlyAccess #FlowbyGoogle #Veo
Try it out at flow.google
J P retweeted
GPT-4o images can now talk.
You can generate a face… and make them speak your script with tone, emotion and timing.
This kills UGC, testimonials, and maybe reality itself.
Here’s how to do it in 30 seconds: 👇
J P retweeted
Watch the behind-the-scenes of NinjaPunk below!
At Promise, we are pioneering a new era of filmmaking.
We’re excited to share a behind the scenes look of our work-in-progress film, NinjaPunk—an original IP we’re building at Promise.
Learn how we integrated Gen AI and 3D-created cityscapes and sets, AI-created characters, and performances from live actors and stunt performers layered into cutting-edge AI/machine learning frameworks.
Gen AI isn’t here to replace the craft of filmmaking—it’s here to expand what’s possible.
Get the full story behind NinjaPunk on our blog: promisestudios.com/post/insi…
J P retweeted
At Promise, we are pioneering a new era of filmmaking.
We’re excited to share a behind the scenes look of our work-in-progress film, NinjaPunk—an original IP we’re building at Promise.
Learn how we integrated Gen AI and 3D-created cityscapes and sets, AI-created characters, and performances from live actors and stunt performers layered into cutting-edge AI/machine learning frameworks.
Gen AI isn’t here to replace the craft of filmmaking—it’s here to expand what’s possible.
Get the full story behind NinjaPunk on our blog: promisestudios.com/post/insi…
J P retweeted
🔥This is a new era of filmmaking!
We’re excited to share a sneak peek of our film, NinjaPunk—an original IP we’re building at @promise_ai.
Set in 2065 Los Angeles, NinjaPunk features Gen AI and 3D-created cityscapes and sets, AI-created characters, and performances from live actors and stunt performers layered into cutting-edge AI/machine learning frameworks.
Gen AI isn’t here to replace the craft of filmmaking—it’s here to expand what’s possible.
Get the full story behind NinjaPunk on our blog. Link in the comments!















