
AI Creation Tools Are Starting to Build Whole Systems
AI creation is moving from one-off assets toward editable systems, tested workflows, and tools builders can actually keep working with…
TRELLIS.2 is a state-of-the-art large 3D generative model (4B parameters) designed for high-fidelity image-to-3D generation. It leverages a novel "field-free" sparse voxel structure termed O-Voxel and a large-scale flow-matching Transformer to reconstruct and generate arbitrary 3D assets with complex topologies, sharp features, and full PBR materials. The model supports images up to 1536³ resolution and outputs textured meshes in GLB/OBJ/FBX/STL formats. Key features include sub-second CUDA conversion (O-Voxel → textured mesh in <100ms) and instant CPU preprocessing (<10s). Released under the MIT license, TRELLIS.2 enables plug-and-play 3D asset generation for indie game developers, CGI artists, and product designers. The model is available on Hugging Face (microsoft/TRELLIS.2-4B) with 100+ Spaces using it for demos, and includes pretrained checkpoints, training code, and a roadmap for shape-conditioned texture generation.
Reader rating
No ratings yet
You might also like
Ogcode is an agentic coding assistant with a web UI, written in Go, that can understand a codebase, plan work with the user, create branches and open pull requests. Its Build Mode lets an agent read, edit and execute code directly, while Plan Mode decomposes larger features or refactors into branch-based tasks that can run in parallel. The tool is for developers who want a more visual, collaborative alternative to terminal-only coding agents. It solves the workflow gap between planning and implementation by keeping tasks, branches and PR creation in one loop. It is notable now because parallel branch agents are becoming a serious way to ship multi-part features faster.
Fabrica is a terminal-based coding agent written in Rust with an interactive TUI, streaming conversation log, in-app model picker, and autonomous file and shell tools. The official README lists multi-provider support for Gemini, Claude, and OpenAI models, plus an agentic loop that can plan and execute multi-step tasks using tool calls until the job is done. It is useful for developers who want a lightweight, hackable coding-agent client outside a full IDE, especially when comparing providers or working in terminal-first environments. Fabrica is notable now because the coding-agent ecosystem is diversifying beyond proprietary editors, and many users want local, transparent tools that can be installed from source or crates.io.
Dreamina is an all-in-one AI image and video generator that transforms simple prompts into stunning visual content. Users can create posters, logos, avatars, videos, and artistic designs from text descriptions or blank canvases. The platform supports both image generation and video creation, making it versatile for content creators, marketers, and designers. Dreamina offers intuitive controls for refining outputs and supports various artistic styles. It is particularly useful for social media content, branding materials, and creative projects requiring high-quality visuals generated quickly.
From the blog

AI creation is moving from one-off assets toward editable systems, tested workflows, and tools builders can actually keep working with…

Kimi K3 in GitHub Copilot shows why open models need more than benchmarks. The models that win are the ones inside real workflows…

Kimi K3 shows why AI competition is shifting from benchmark wins to default integrations inside coding tools and inference platforms…