Local AI · Topic hub
Local Video
Wan, HunyuanVideo, LTX and ComfyUI — open-weight video on consumer hardware.
24 articles across guides, comparisons, prompts, tools
Guides15
All guides →
GuidesRun Stable Diffusion Locally: Setup That Works in 2026
SD1.5 vs SDXL VRAM math, the ComfyUI desktop install, your first workflow, where checkpoints come from, and the errors that eat everyone's first afternoon.
GuidesAI B-Roll: Never Pay for Stock Footage Again (2026 Guide)
We build our b-roll library locally on an RTX 4080 running Wan 2.2 — real render times, prompt patterns by niche, and the math against a stock subscription.
GuidesWan 3.0 Release Date: What's Confirmed vs SEO Fiction (2026)
Alibaba confirmed Wan 3.0's public beta on August 7, 2026 — 30-second clips, document inputs. We audit which Wan 2.7 and 3.0 claims are real vs SEO fiction.
GuidesWan 3.0 Complete Guide: Alibaba's 30-Second AI Video (2026)
Wan 3.0 entered public beta in August 2026 with 30-second clips and document-to-video. Every confirmed spec, verified sources, and what's still unknown.
GuidesStable Audio 3 Local Setup: Run the Open Weights on Your GPU
Stable Audio 3's open-weight models run on consumer hardware. The Hugging Face repos, the stable-audio-3 library, license limits, and what a 4080 can expect.
GuidesPoolside Laguna XS 2.1: A 33B Coding Model for One GPU
Poolside's Laguna XS 2.1 activates just 3B of its 33B parameters per token, enough for real agentic coding on a single consumer GPU. Specs and setup.
GuidesQwen3.8-Max: What's Confirmed and What Isn't Yet (2026)
Alibaba's 2.4T-parameter Qwen3.8-Max went live August 3 as a hosted API only. Open weights for it and a 27B sibling are due next week: the real spec sheet.
GuidesWan 2.2 Animate: Character Animation on Your GPU (2026)
Wan 2.2 Animate transfers a real performance onto any character image, motion and expressions included. ComfyUI setup, VRAM tiers, and mode choice.
GuidesRun MiniMax H3 Locally: Open Weights in ComfyUI (2026)
MiniMax H3's open weights are live. What you actually download, the 42.5GB ComfyUI footprint, the 12GB claim, and which parts stay hosted-only.
GuidesRun LTX-2 Locally: AI Video With Audio on 16GB (2026)
LTX-2 generates video and synced audio in one pass on your own GPU. The real VRAM tiers, the 2.3 update, ComfyUI setup, and where 16GB cards hit limits.
GuidesFLUX 3: What's Confirmed and What Isn't Yet (2026)
Black Forest Labs launched FLUX 3 on July 23: 20-second video with native audio, gated early access, an open-weight Dev promise. The confirmed spec sheet.
GuidesOpen-Weight AI Video Models You Can Actually Run
MiniMax H3 going open-weight restarts this argument. What runs on 8GB, what needs 24GB, and what the quantization actually costs you in quality.
GuidesMiniMax H3 Guide: 2K Video, Native Audio & Open Weights
MiniMax H3 landed July 31 with native 2K, built-in dialogue and open weights. The real API limits, the five input modes, and where it still breaks.
GuidesHunyuan 3 Local Guide: Can You Actually Run 295B at Home?
Tencent open-sourced Hunyuan 3 — 295B total, 21B active, Apache-2.0. We break down the real VRAM math, the GGUF quant path, and who should skip it entirely.
GuidesRun Wan 2.2 Locally: Free AI Video on Your Own GPU (2026)
Our exact local Wan 2.2 setup on an RTX 4080: GGUF quantization, the Triton + SageAttention + TeaCache speed stack, and the mistakes that waste a weekend.
Comparisons5
All comparisons →
ComparisonsComfyUI vs Automatic1111 in 2026: Which UI Wins?
AUTOMATIC1111's last tagged release was Feb 2025; ComfyUI ships weekly and had Flux, Wan and Qwen-Image support first. We compare both on real repo data.
ComparisonsWan 3.0 vs Wan 2.7: What Actually Changed in 2026
Wan 3.0 vs Wan 2.7 from official Alibaba sources only: 30-second clips, document-to-video, what the beta really adds over 2.7 and 2.6, and who should switch.
ComparisonsMiniMax H3 vs Wan 2.2: Open-Weight Video King (2026)
Both are open weights now. One fits a 16GB card today, one generates 2K with native audio if you can feed it. Where each wins, with the VRAM math.
ComparisonsMiniMax H3 vs Seedance 2.5: Live API vs 30s Takes
Two frontier video models shipped on July 31. One has a documented public API at 2K, the other has 30-second takes and no published specs at all.
ComparisonsKimi K3 vs GLM-5.2 (2026): Open-Weight Heavyweights Compared
Moonshot's 2.8T-parameter Kimi K3 against Z.ai's 744B GLM-5.2 — benchmarks, token pricing, agentic coding and what it takes to run each one yourself.
Prompts1
All prompts →
Tools3
All tools →
ToolsWhere to Run MiniMax H3: Every Route Compared
H3 is on MiniMax's own API, fal, ComfyUI, Vercel AI Gateway, OpenRouter and a dozen resellers. What each route actually gives you, and what it costs.
ToolsStable Audio 3.0 Tool Hub: Facts, Licensing & Our Verdict
Stability AI's Stable Audio 3.0: the four-model lineup, real inference numbers, what 'open-weight but licensed' means, and who should pick it over Suno or Udio.
ToolsComfyUI — Tool Hub: Facts, Best Tutorials & Verdict
Everything about ComfyUI in one place: the node-based local studio for image and video generation, VRAM needs, limits, best tutorials, and our workflow library.