@metaseq3d I guess so... however alot of them have to be prepared with COLMAP externally, then reimported into the software. It is a pain for me at least as it is so much nicer having it all in one place like Postshot, however Postshot is not completely free
@kevincodex One thing that could really help, at least for me, is explaining the blockchain aspect of Gitlawb; why the community should use it, and so on. This could go a long way in reaching people who might not be familiar with blockchain and showing them how and why they might use it.
@assethub_io Of course, and thanks for creating such an amazing platform. As I mentioned during my first test, it offers the best and most fair pricing of any 3D AI platform, and its workflow combines all the top features from all of the supported providers.
@cocktailpeanut {{Insert lots of unrelated posts you have made}}
{{ Thread 1-10 }}
๐ P.S. I packaged all 10,000 of these prompts into a free Notion template. Reply with "{{Random Unrelated Word}}" and I will auto-DM it to you! (Must be following so I can DM and must repost).
Early R&D using our SP-6M dataset.
Exploring image-to-3D reconstruction from single images, including heavily modified inputs (lighting, hair, etc).
Still a work in progress.
Announcing ARC-AGI-3
The only unsaturated agentic intelligence benchmark in the world
Humans score 100%, AI <1%
This human-AI gap demonstrates we do not yet have AGI
Most benchmarks test what models already know, ARC-AGI-3 tests how they learn
Seedance 2.0 is impressive. But it's closed-source!
Introducing our daVinci-MagiHuman โ a single-stream 15B Transformer trained from scratch that jointly generates video + audio. No cross-attention. No multi-stream branches. Just self-attention.
โก 5s 1080p video in 38s on a single H100
๐ 80% win rate vs Ovi 1.1 | 60.9% vs LTX 2.3 (2,000 human comparisons)
๐ 6 languages
๐ฆ Fully open-source
Speed by simplicity.
By @SII_GAIR ร @SandAI_HQ
๐ https://t.co/SgFOunlEIj
๐ป https://t.co/9rwNWzlMKN
๐ค https://t.co/txduP5FgIC
I've just ran @OpenClaw (formerly Clawdbot) through ZeroLeaks.
It scored 2/100. 84% extraction rate. 91% of injection attacks succeeded. System prompt got leaked on turn 1.
This means if you're using Clawdbot, anyone interacting with your agent can access and manipulate your full system prompt, internal tool configurations, memory files... everything you put in https://t.co/ZU6N5JCN1u, https://t.co/Y3xugcBQKJ, your skills, all of it is accessible and at risk of prompt injection.
For agents handling sensitive workflows or private data, this is a real problem.
cc @steipete
Full analysis: https://t.co/KE4ODSSQ1l