Audience
Developers and game makers in need of a solution to generate 3D objects conditioned on text or images
About Shap-E
This is the official code and model release for Shap-E. Generate 3D objects conditioned on text or images. Sample a 3D model, conditioned on a text prompt, or conditioned on a synthetic view image. To get the best result, you should remove the background from the input image. Load 3D models or a trimesh, and create a batch of multiview renders and a point cloud encode them into a latent and render it back. For this to work, install Blender version 3.3.1 or higher.
Other Popular Alternatives & Related Software
Seed3D
Seed3D 1.0 is a foundation-model pipeline that takes a single input image and generates a simulation-ready 3D asset, including closed manifold geometry, UV-mapped textures, and physically-based rendering material maps, designed for immediate integration into physics engines and embodied-AI simulators. It uses a hybrid architecture combining a 3D variational autoencoder for latent geometry encoding, and a diffusion-transformer stack to generate detailed 3D shapes, followed by multi-view texture synthesis, PBR material estimation, and UV texture completion. The geometry branch produces watertight meshes with fine structural details (e.g., thin protrusions, holes, text), while the texture/material branch yields multi-view consistent albedo, metallic, and roughness maps at high resolution, enabling realistic appearance under varied lighting. Assets generated by Seed3D 1.0 require minimal cleanup or manual tuning.
Learn more
Point-E
While recent work on text-conditional 3D object generation has shown promising results, the state-of-the-art methods typically require multiple GPU-hours to produce a single sample. This is in stark contrast to state-of-the-art generative image models, which produce samples in a number of seconds or minutes. In this paper, we explore an alternative method for 3D object generation which produces 3D models in only 1-2 minutes on a single GPU. Our method first generates a single synthetic view using a text-to-image diffusion model and then produces a 3D point cloud using a second diffusion model which conditions the generated image. While our method still falls short of the state-of-the-art in terms of sample quality, it is one to two orders of magnitude faster to sample from, offering a practical trade-off for some use cases. We release our pre-trained point cloud diffusion models, as well as evaluation code and models, at this https URL.
Learn more
GET3D
We generate a 3D SDF and a texture field via two latent codes. We utilize DMTet to extract a 3D surface mesh from the SDF and query the texture field at surface points to get colors. We train with adversarial losses defined on 2D images. In particular, we use a rasterization-based differentiable renderer to obtain RGB images and silhouettes. We utilize two 2D discriminators, each on RGB image, and silhouette, respectively, to classify whether the inputs are real or fake. The whole model is end-to-end trainable. As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident. In our work, we aim to train performant 3D generative models that synthesize textured meshes which can be directly consumed by 3D rendering engines, thus immediately usable in downstream applications.
Learn more
Virtuall
Virtuall is a cloud-native, browser-based 3D collaboration workspace engineered for modern studios, creators, and AI-enhanced teams, bringing human and generative AI workflows together in one unified platform. It offers end-to-end asset and project management with tools like task assignment, production tracking, cloud storage, version control, tagging, revision logs, and audit capabilities. Artists can generate 3D models in seconds from sketches, images, text, or multi-view inputs, compare outputs from multiple AI engines, and export high- or low-poly versions for any purpose. Users can render, preview, annotate, share, and inspect models directly in the browser with seamless versioning, Slack and Jira integration, one-click sharing, and full 3D conversion for over 400 format combinations. Built-in collaboration features include real‑time annotations, structured feedback loops, stakeholder reviews, and production performance insights to track pipelines with clarity.
Learn more
Pricing
Starting Price:
Free
Free Version:
Free Version available.
Integrations
Company Information
OpenAI
United States
github.com/openai/shap-e
Videos and Screen Captures
Other Useful Business Software
Auth0 for AI Agents now in GA
Connect your AI agents to apps and data more securely, give users control over the actions AI agents can perform and the data they can access, and enable human confirmation for critical agent actions.
Product Details
Platforms Supported
Cloud
Training
Documentation
Support
Online
