Set it up, size it, ship it.
How-to Guides
How-to guides are the implementation companion to the buyer's guides. Once you've chosen hardware, these answer the operational questions: how much VRAM does this checkpoint actually use, which sampler and resolution combo is realistic, how do you wire two cards in ComfyUI, and what does each runtime do differently in 2026.
How this category works
We focus on questions where the answer changes month-to-month: VRAM math after the latest Flux release, ComfyUI node ecosystem updates, sampler choices for SDXL 1.5 versus Flux Schnell, and how AnimateDiff and HunyuanVideo memory profiles compare on consumer hardware.
Every guide has been written against a real reference setup we can actually run — SDXL on a single 12GB card, Flux on a 16GB+ card, video models on a 24GB card. When we cite a seconds-per-image or seconds-per-frame number, the body of the article links to the underlying chart so you can audit the methodology rather than trust a headline number.
If you're new to local AI image and video, the VRAM planning, runtime selection, and quantization guides are the trio to read first — they remove ninety percent of the uncertainty before you spend on hardware.
Featured
Where most readers start
The 5 highest-leverage guides in this category — the ones that answer the most common reader questions.
- 01
- 02
- 03
- 04
- 05
Browse 25
Every article in How-to Guides
Filter or search the full list. Sorted newest-first by default.
Other lanes