Peaked at #3 Now #4
Open-source image-to-3D model Idol
Speridlabs releases Idol, a 600M-param open image-to-3D model using under 7.2GB VRAM.
Key points
- Speridlabs released Idol, an open image-to-3D model described as a 3D-DiT that generates complete 3D objects from a single image.
- Idol is pre-trained from scratch with only 600M parameters, runs on consumer GPUs using less than 7.2 GB of VRAM, and can generate 1M splats in 3 seconds.
- Speridlabs said the weights, code and demo are fully open under Apache 2.0.
- The original poster shared links to the weights and code.
Key points and the reaction summary are written by AI from the posts on this page. Check the original post. How we use AI
Original post
Meet Idol, an open image-to-3D model. A 3D-DiT that generates complete 3D objects from just an image.
Pre-trained from scratch, contains only 600M parameters, it runs on consumer GPUs, using less than 7.2 GB of VRAM and can generate 1M splats in 3 seconds. Try it today.
Fully open: weights, code and demo (Apache 2.0)
https://t.co/Cf0slnSI5C
Top replies on X
Reaction on X: Replies were mostly positive, with one calling it a good job and noting it holds up from every angle, and another suggesting it pairs well with Radix. One reply questioned the value of 3D objects that output splats, and one commenter noted "Made in 🇪🇸". The original poster replied with links to the weights and code.
Sign in to see 5 top replies from X
From @speridlabs, @jalvarezz13, @GuliMoreno and others. Spam removed, with English and Chinese translations.
Discussion 0
Sign up Sign in to join the discussion
No comments yet. Start the conversation.