What bugs did you encounter? And yes, because we're using actual 3D models, there's a fixed set of models (right now, just under 300). Because the priority is ultra-realism, the current state-of-the-art for 3D model diffusion won't cut it (see OpenAI Point-e https://github.com/openai/point-e). - Source: Hacker News / 9 months ago

The mesh was generated with a prompt generated from GPT using an online implementation of Point-E at https://magus.gg/imagine. Source: about 1 year ago

2D image to 3D point cloud converter. Can be AI-based or manual implementation. I tried point-e from OpenAI but it's not producing expected results. Source: over 1 year ago

Craftwork → 50% off on UX/UI kits, illustrations, graphics and all access subscriptions → https://craftwork.design. Source: over 2 years ago

Shoutouts to Craftwork.design For the illustrations. Were used as samples. After this poll ends, I pick a license and request modifications and edits by contacting Craftwork studio. Those are good fellas! Source: over 2 years ago

These are not high-quality illustrations, but garbage (pardon those words). The best illustrations are right here: Https://icons8.com/illustrations Https://storytale.io/ Https://craftwork.design/. Source: almost 3 years ago

Craftwork: Interface assets for designers and startup creatives. Source: almost 3 years ago