3D printed figures: getting a printable mesh without a sculpting degree
Four routes to a figure mesh, the repair pass a slicer quietly expects, and the resin versus FDM decision, with typical numbers for scale, wall thickness and layer height.
Guides, reviews and 3D workflow notes
Practical writing on AI 3D generation, printing, game art and the tools around them.
Tutorial
Tutorial
How to export a 3D model: picking between GLB, glTF, OBJ, STL and FBX
Export is a decision about the next application, not about file size. What GLB, glTF, OBJ, STL and FBX each carry, what they quietly drop, and how FBX is reached when a generator does not offer it.
Tutorial
How to generate a 3D model from an image: the four decisions that shape the result
Image-to-3D predicts the geometry the camera never saw. Here is how to prepare the photo, choose between single-view and multiview engines, judge the mesh in the first minute, and export it at the right scale.
Tutorial
How to generate reference images for 3D: the four questions that decide the mesh
A stock photo gives you someone else's product in dramatic light. A generated reference gives you the viewpoint, lighting and silhouette the image-to-3D step actually needs. Here is the pipeline, the engine trade-offs and the prompt recipe.
Tutorial
How to imprint an image on a 3D model: four methods, four different failure modes
Raising the picture out of the surface, cutting it in, projecting it as a texture and letting it control material thickness are four separate jobs with different tools and different numbers. Here is what each one needs and how to check it before printing.
Tutorial
How to make a 3D model: four routes, the tools for each, and what you export
AI generation, polygonal modelling, parametric CAD and scanning all end in a mesh, and they disagree about cost, control and what the file is good for afterwards. Here is how to pick a route and what the first hour looks like.
Tutorial
3D Print a Person From a Photo: What Actually Works in 2026
A photograph carries no depth, so the printed result depends on how much the software is allowed to guess. This guide covers capture, three routes to a printable solid, the mesh checks that matter, and the scale and wall thickness a small figure needs.
Tutorial
Installing TRELLIS 2 in ComfyUI on Windows: the RTX 50-series route from driver to first mesh
TRELLIS 2 arrives as a node package plus three CUDA extensions that compile on your own machine, and an RTX 50-series card changes which toolkit and which PyTorch wheel will work. This is the install order, the environment variables, and the fixes for the errors you will actually hit.
Tutorial
Trellis 2 ComfyUI workflow download: reading the JSON, repairing a graph, and the four common variants
A downloaded TRELLIS 2 workflow is one JSON file describing node types, links and widget values. Most first-load failures come down to four things: a missing node pack, a weight filename that no longer matches, widget values that shifted between pack versions, and a VRAM budget only the GGUF variant fits.
Tutorial
TRELLIS 2 in ComfyUI: the model, the wheel stack and both workflow builds
TRELLIS 2 is a 4B-parameter image-to-3D model, and its ComfyUI wrapper depends on compiled CUDA extensions that must match your Python, torch and CUDA versions. This hub covers what it produces, what a machine needs, and how both workflow builds are assembled.
Tutorial
TRELLIS 2 multiview workflow in ComfyUI: a 4-6 view camera ring, wired step by step
Single-image 3D generation has to invent the back of the object. This walkthrough covers how the TRELLIS 2 multiview stage in ComfyUI turns one picture into a ring of consistent angles, how to lay out the camera views, and how to decide whether the extra VRAM is worth it.
Tutorial
How to make a 2D image 3D: pick the goal first, then the method
A single photo can become a game asset, a printable relief or a measured scan, but not all three at once. Here are the four goals, the method each one needs, and the cleanup each one costs.