BudgetAny family extends BudgetPix to image-to-3D with one checkpoint, multiple inference budgets
anand_bhattad · x · 2026-11-14
The team released the BudgetAny family, extending BudgetPix from image generation to image-to-3D, with more modalities planned. Budget3D distills Sperid Labs' Idol and Idol-turbo models to process fewer tokens, letting a single checkpoint run at multiple compute budgets at inference. Project page, GitHub repo, and Hugging Face weights are all available.
More from Multimodal
- ByteDance releases Seedance 2.5 Flash video model at 35% off — videorouter · 2026-11-14
- OpenAI Images 2.6 tops DesignArena and Image Arena at 4s per image, same price — thursdai_pod · 2026-11-14
- MiniMax H3 Camera & Motion Control Tested on a RTX 4070 with Only 8GB VRAM — big-boss_97 · 2026-11-14
- 3D scene gen comparison: Inkling 2 Small cinematic, Kimi K3 bland — LiTianleli · 2026-11-14
- Anthology episode '2000' made entirely with AI tool Cuelist — Uncanny_Harry · 2026-11-14
- Google Flow's Omni 1.2 Flash Makes a Full 15-Second Beverage Ad from One Prompt — Emergency_Abies_6508 · 2026-11-14