Wan video model
Hacker ApprovedRanked 5 of 9 AI video generators by recommenders
Open-weights AI video generator praised for output quality and running on home hardware. Most common caveat: local runs are cumbersome and need a lot of memory.
Open-weights AI video generator praised for output quality and running on home hardware. Most common caveat: local runs are cumbersome and need a lot of memory.
19 people gave an opinion
- recommend it
- 15
- criticize it
- 4
- approval share
- 79%
Recommended in 7 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 15 people recommend itNeeds 10 or more, met.
- 3.8 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 7 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Good output quality and realism
“The interface is easy to navigate, the results are consistent, and the output quality fits well across different platforms”
Comment from 17 Dec 2025 in “A Simple Way to Create Festive Videos This Holiday Season” “it delivers smooth motion, stable character consistency, and impressive visual realism”
Comment from 10 Dec 2025 in “Create High-Quality AI Videos Effortlessly with Wan 2.6” “still the most powerful Video inference out there, to the level of quality it provides”
Comment from 27 Apr 2026 in “China blocks Meta's acquisition of AI startup Manus” Accessible on home hardware
“offers a practical and accessible option worth checking out”
Comment from 30 Dec 2025 in “AI Video Generation Made Easier with Wan 2.6” “even older WAN could easily handle this”
Comment from 15 May 2026 in “Cut Off: why access to frontier AI will soon be scarce and selective” “try out wan2.2 on their home computer”
Comment from 5 Jan 2026 in “All AI Videos Are Harmful (2025)”
What people warn about
Each mark is one comment
Heavy hardware needs and memory limits
“they are interesting: however actually running those types of models is too cumbersome”
Comment from 13 Nov 2025 in “Nano Banana can be prompt engineered for nuanced AI image generation” “I was running into OOM issues with Wan 2.2 before”
Comment from 26 Dec 2025 in “Show HN: Fun sketch – Animate your sketches” Output weaker than other versions
“seem significantly worse than what I’ve seen from WAN 2.1 1.3B”
Comment from 2 Dec 2025 in “Apple Releases Open Weights Video Model” “video diffusion models (like Wan2.2 and LTX-2) often suffer from non-linear semantic evolution”
Comment from 27 Apr 2026 on Hacker News “It's Wan video, which is a shitty video model.”
Comment from 16 Jul 2026 in “$100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol”
Other AI video generators people recommend
The four most recommended other AI video generators, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Seedance 2.0 | 68 | 21 | 76% | 10 | — | Approved |
| MiniMax H3 | 29 | 11 | 73% | 3 | — | — |
| Google Veo | 20 | 11 | 65% | 8 | — | — |
| Gemini Omni | 16 | 21 | 43% | 2 | — | — |
| Wan video modelThis page | 15 | 4 | 79% | 7 | — | Approved |
What people said
All 22 comments that mention it, newest first. Each links to the original comment.
“Those are completely worthless to me now.”
“It's Wan video, which is a shitty video model.”
“I wouldn't do anything production grade in Wan.”
“those guys know more about WAN 2.2 than the people who trained it”
“All great for creation pipelines.”
“even older WAN could easily handle this”
“still the most powerful Video inference out there, to the level of quality it provides”
“video diffusion models (like Wan2.2 and LTX-2) often suffer from non-linear semantic evolution”
“Wan 2.2 did a rug pull, left a huge gap for the community that built around Wan 2.2 too”
“I can generate a 5 second clip with wan 2.2 in about 30 minutes on my 3060 12G.”
“try out wan2.2 on their home computer”
“offers a practical and accessible option worth checking out”
“I was running into OOM issues with Wan 2.2 before”
“2s to generate a 5s video on a 5090 for WAN 2.1 is absolutely crazy”
“The interface is easy to navigate, the results are consistent, and the output quality fits well across different platforms”
“it delivers smooth motion, stable character consistency, and impressive visual realism”
“Our main differentiator is native audio sync.”
“seem significantly worse than what I’ve seen from WAN 2.1 1.3B”
“video models that are worse than Wan 2.2”
“Right now WAN is only behind Google's Veo in image-to-video rankings on llmarena”
“It worked out because I didn't have specific demands other than what I just said”
“they are interesting: however actually running those types of models is too cumbersome”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.