HN Showcase
Back to browse
Meshcraft – Text-to-3D and image-to-3D with selectable AI engines

Meshcraft – Text-to-3D and image-to-3D with selectable AI engines

by otmardev·Mar 7, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidEye CandyCrowd Pleaser

Multi-engine 3D generation with PBR export, but Meshy.ai, Masterpiece Studio, and Luma already own this space.

Strengths
  • •Switchable engines (Trellis 2 free, Hunyuan v3.1 Pro paid) with transparent credit pricing lets power users pick speed vs quality trade-off.
  • •PBR materials + clean ~50K-quad topology vs vertex colors means exports actually work in game engines without artist cleanup.
  • •Four text-to-image options upstream (FLUX, GPT-4 variants) gives real flexibility for different prompt types and quality needs.
Weaknesses
  • •3D generation from images/text is saturated market (Meshy.ai, Luma, Rodin.ai, Trellis direct); no novel technical claim beyond picking better existing models.
  • •Credit pricing (1-59 per generation) positions against free-tier competitors; unclear competitive advantage beyond UI polish.
Category
AI/ML
Target Audience

Game developers, 3D artists, 3D printing enthusiasts, content creators

Similar To

Meshy.ai · Masterpiece Studio · Luma.ai

Post Description

Hey HN, I built Meshcraft – a web-based tool that generates 3D models (GLB) from text prompts or images.

What's new since the first Show HN (Feb): Back then it was a basic TripoSR wrapper. A commenter here (thanks vunderba) pointed me to Trellis 2, which was vastly better. Since then I've rebuilt the whole thing:

- Two 3D engines: Standard (Trellis 2 via HuggingFace ZeroGPU) and Premium (Hunyuan v3.1 Pro via fal.ai). Standard is free, Premium costs 50 credits and produces ~1.4M face models with proper PBR materials. - Four image models for text-to-3D: FLUX 1 Schnell, FLUX 2 Dev, GPT Image 1 Mini, GPT Image 1.5. You pick the model, type a prompt, and it generates an image then converts to 3D. - Unified credit system with variable costs per action (1-59 credits depending on engine + image model combo).

Stack: Next.js 16 on Netlify, Supabase (auth + DB + storage), Stripe, HuggingFace ZeroGPU H200, fal.ai serverless for Hunyuan and image generation. Background generation via Netlify Background Functions (up to 15 min async).

What I learned building this:

1. The 3D engine is the quality bottleneck, not the image model. I tested 8 engines before settling on two. Trellis 2 is great for simple objects but struggles with complex geometry (missing fingers, back-side artifacts). Hunyuan v3.1 Pro solves most of these. 2. Image model quality matters less than you'd think for 3D – a $0.003 FLUX schnell image produces nearly the same 3D result as a $0.009 GPT Image 1.5 image. 3. HuggingFace ZeroGPU is incredible for bootstrapping – free H200 inference with a $9/mo Pro account. The cold start and queue times are the trade-off.

Free tier: 5 credits/month, no credit card required. Would love feedback on the generation quality and UX.

Similar Projects