Takuya

122 posts

Takuya banner
Takuya

Takuya

@task5622

Building @AssetHub_io (The Best Way to Create 3D with AI) // prev Co-founder & CTO of https://t.co/WpZXYGdnB8 ($20m+ raised from Sony, Sanrio) // 🇯🇵 @PTeamd

San Francsico, CA 가입일 Mart 2014
207 팔로잉240 팔로워
Takuya 리트윗함
Alex
Alex@alexfredo87·
I'm testing AI texture projection on low poly characters for my mobile VR game.
English
23
22
563
51.3K
Carolina Delgado
Carolina Delgado@carolletta·
It is time to flash your AI Art! Share your AI Art - Any subject Like 💛, repost 🔁, follow & tag @ your friends ⭐️!
English
86
13
106
2.7K
robot
robot@alightinastorm·
thinking about starting a group chat on X with AI-first game devs No AI haters allowed reply if you want in, minimum 100 or we cancel the idea no need for another ghost gc
English
307
10
423
38K
Takuya 리트윗함
Jerome | InsaneUnreal
Jerome | InsaneUnreal@insaneUEFN·
Whah these two guys don't know what's coming! 🦖 Made with a bunch of tools including Kling 3.0 Crazy how we can get the characters very consistent! First time trying to get a couple of generated shots into a storyline that makes sense. Big challenge lol! If you see any AI shortfilm that has story, consistent character placement, spatial logic; that person has done a great job haha Oh btw you can try making logo reveals by setting a black first frame and logo design as last frame.
English
2
2
13
1.7K
Takuya
Takuya@task5622·
@assethub_io split image -> multi-view -> generate by parts -> merge it on blender
English
1
0
2
37
Takuya 리트윗함
AssetHub
AssetHub@assethub_io·
What's the best workflow for AI to 3D 2026?
English
3
1
4
197
Takuya 리트윗함
Jerome | InsaneUnreal
Jerome | InsaneUnreal@insaneUEFN·
Generating flipbooks in ComfyUI. Nothing too crazy, but these little AI workflows are definitely helpful! 🐦 When I input a black frame to the FirstLastFrame node I got some decent impulse textures. using Wan 2.2 btw. For the bird to work i had to generate between 30-60 frames and extract every 4 frames to get better wing motion. In UEFN / Unreal Engine i'm offsetting the animation phase for every particle to get a more random result.
English
5
18
214
11K
Takuya
Takuya@task5622·
thanks and yes absolutely! that demo was like AI thinks the workflow and does it first for you. but you can customize your own workflow and instant split image, multi view gen, or those by 1 click as well like this for example. I'm researching workflow / usecases of advanced ppl like yours and would love more of your take. would you be open to a casual call? not to sell but to research to make something useful for the industry.
English
0
0
0
26
Jerome | InsaneUnreal
Jerome | InsaneUnreal@insaneUEFN·
@task5622 that looks great! I guess you can instant split to parts if you know you want to right?
English
1
0
1
72
Takuya 리트윗함
Jerome | InsaneUnreal
Jerome | InsaneUnreal@insaneUEFN·
From generated reference images to riding a robot raptor in Fortnite 🦖 For now mostly the same workflow, but I also used Nano Banana to get that toe claw in the image lol. Other steps: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing and AI upscaling. Blender for cleanup, rigging and weight painting. Splitting up the body parts helped to get a more mid-poly result. Also with better control during cleanup. The final result has 28K triangles. Again with the awesome retargeting tools in Unreal Engine / UEFN. I’ll be testing different AI texturing approaches soon. Some parts can get a bit wobbly at times, most notable in hard-surface objects. Also curious if there are any upcoming weight painting tools 😄
English
19
55
665
40.2K
Takuya
Takuya@task5622·
I see. I'm building a function to automate those. like AI analyzes a reference image -> decides the best next step (this case is part split) -> split parts auto -> give feedback to iterate (human in the loop) Do you think this is something helpful to save your time? Your workflow is exactly what I have hypothesized. Would love your honest feedback.
English
1
0
0
64
Jerome | InsaneUnreal
Jerome | InsaneUnreal@insaneUEFN·
@task5622 Started with 1 reference image and asked to make new images with only the parts separate
English
1
0
2
352
Takuya
Takuya@task5622·
got many leads from a conference in asia. we're on the right track. didn't sleep for a while...
English
1
0
3
147
Henry Shi
Henry Shi@henrythe9ths·
I got rejected by 144 investors before raising $150M for my $200M+ rev/year startup. After 144 rejections, I started questioning our approach. Were we solving the right problem? What were we doing wrong? Why weren’t investors seeing what we were seeing? Were we the right team to build this? We tried everything: different pitch angles, new deck structures, and reframing the problem. Then came the 145th meeting, where we closed our first growth round. That yes made everything worth it. But getting there took years of mistakes and hard work. We went through a lot of trial and error just to figure out what resonates with investors. We tried dozens of approaches to figure out what made investors engage. Some landed, most didn't. But each iteration taught us something about what builds conviction versus what just sounds good on paper. And once we cracked that code, our Series C closed faster than expected. And today, I see so many founders in the exact same position I was in 10 years ago: grinding through rejections, questioning everything, and trying to figure out what works. So today I want to give you the resource I wish I had back then: Something that shows you exactly how to structure these conversations and navigate the entire process (because the fundraising cycle can be a big distraction and take a toll on you as a founder). So I've partnered with Notion's Startups Team to create the essential fundraising resource that helps you avoid the mistakes that cost me years. Here's what you are getting: • The actual decks I used to raise $150M for Super[.]com (Series B, C) • 50 real examples from funded startups like Eleven Labs and Artisan AI • A searchable database of 10,000+ investors - angels, VCs, and accelerators you can reach out to immediately (this alone would take months to build manually) • An AI-powered fundraising agent built into Notion with step-by-step prompts (no separate ChatGPT needed) Want access? • Like and share this post • Comment "FUNDRAISE" • Follow me so I can DM you the link I'll send it over ASAP. P.S.: If you are serious about fundraising (now or in the future), you should grab it right away.
English
3.2K
926
4.4K
555.3K
Ben Lang
Ben Lang@benln·
I’d love to angel invest in a few more companies before 2025 ends. If you think I’d make a good addition to your cap table, reach out, DMs are open.
English
161
38
915
113.4K