{"slug": "wan", "name": "Wan", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 8, "warners": 0, "score": 3.798, "rising": -0.98, "first": "2025-11-18", "latest": "2026-09-11", "why": "I recently used WAN to generate a looping clip of clouds moving quickly", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 5, "compare": 1, "warn": 0}, "spark": [1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I recently used WAN to generate a looping clip of clouds moving quickly", "kind": "", "icon": true, "domain": "wan.video", "github_repo": null, "official_url": "https://wan.video/", "pricing": "", "aliases": ["Wan 2.2", "WAN", "Wan", "Wan 2.1", "Wan2.1"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 770480225, "item_id": 48155014, "url": "https://news.ycombinator.com/item?id=48155014", "by": "vunderba", "date": "2026-05-15", "stance": "recommend", "quote": "or even older WAN could easily handle this", "excerpt": "Local text-to-vid such as LTX Video 2.3 or even older WAN could easily handle this then combine with something like SeedVR2 to upscale. https://github.com/Lightricks/ComfyUI-LTXVideo", "context": "", "use_case": "", "switched_from": "", "story": "Cut Off: why access to frontier AI will soon be scarce and selective"}, {"id": 760218337, "item_id": 47513646, "url": "https://news.ycombinator.com/item?id=47513646", "by": "EugeneOZ", "date": "2026-03-24", "stance": "recommend", "quote": "There are open-source alternatives:", "excerpt": "There are open-source alternatives: https://mochi1ai.com/ https://wan.video/ and others. There are free to use tools also.", "context": "", "use_case": "", "switched_from": "", "story": "OpenAI set to discontinue Sora video platform"}, {"id": 735577088, "item_id": 45973568, "url": "https://news.ycombinator.com/item?id=45973568", "by": "Uehreka", "date": "2025-11-18", "stance": "recommend", "quote": "I recently used WAN to generate a looping clip of clouds moving quickly", "excerpt": "I design projections for independent theatre in Baltimore. I use AI in my workflows where it can help me and won\u2019t compromise on the quality of what I\u2019m making. I frequently use AI to upscale crappy footage, to interpolate frames in existing video (for artistic purposes, never with documentary archival stuff) and very occasionally to create wholesale clips in situations where video models can do what I need. I recent", "context": "", "use_case": "", "switched_from": "", "story": "Blender 5.0"}]}], "caveats": [], "who": [{"by": "jabrotapu", "context": "freelancer building on-prem GPU clusters", "url": "https://news.ycombinator.com/item?id=49661006", "date": "2026-09-11"}], "tags": [], "use_cases": ["video generation", "local video generation", "image-to-video generation"], "compared": [{"slug": "ollama", "name": "Ollama", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "comfyui", "name": "ComfyUI", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "prometheus", "name": "Prometheus", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "flux", "name": "FLUX", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "open-webui", "name": "Open WebUI", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "stable-diffusion", "name": "Stable Diffusion", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "qwen", "name": "Qwen", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "grafana", "name": "Grafana", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49522905", "title": "Ask HN: Freelancer? Seeking freelancer? (September 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48646659", "title": "Krea 2 Technical Report", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48143284", "title": "Cut Off: why access to frontier AI will soon be scarce and selective", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47601858", "title": "Ask HN: Who wants to be hired? (April 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47508246", "title": "OpenAI set to discontinue Sora video platform", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46992081", "title": "BleuNova \u2013 Ethical self-hosted AI agent (privacy-first)", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {"compare": 1, "neutral": 1}, "2026-01": {}, "2026-02": {"neutral": 1}, "2026-03": {"recommend": 1}, "2026-04": {"neutral": 1}, "2026-05": {"recommend": 1}, "2026-06": {"neutral": 1}, "2026-07": {}, "2026-08": {}, "2026-09": {"neutral": 1}, "2026-10": {}}, "quotes": [{"id": 794576107, "item_id": 49661006, "url": "https://news.ycombinator.com/item?id=49661006", "by": "jabrotapu", "date": "2026-09-11", "stance": "neutral", "quote": "ComfyUI, Flux, Wan 2.1, Stable Diffusion", "excerpt": "SEEKING WORK | India, remote | Part-time | Overlap with US, UK, EU hours I build on-prem GPU clusters and private AI apps that run entirely on the client's own hardware, so their data never leaves the building. About 10 years full-stack, the last few on GPU infrastructure. Currently running a live production cluster: 700-800 users sharing a small physical GPU pool. GPU-backed JupyterHub, single sign-on, per-user quot", "context": "freelancer building on-prem GPU clusters", "use_case": "video generation", "switched_from": "", "story": "Ask HN: Freelancer? Seeking freelancer? (September 2026)"}, {"id": 778854515, "item_id": 48678407, "url": "https://news.ycombinator.com/item?id=48678407", "by": "Eisenstein", "date": "2026-06-25", "stance": "neutral", "quote": "Wan2.1 safetensors as the VAE", "excerpt": "Rolling build of Koboldcpp now supports Krea2: * https://github.com/LostRuins/koboldcpp/releases/tag/rolling Model weights: * https://github.com/leejet/stable-diffusion.cpp/blob/master/docs/krea2.md In the launcher GUI, select 'Image Gen' and set Krea2 Turbo gguf as the image model, Qwen3 VL 4b gguf as the T5 model, and Wan2.1 safetensors as the VAE.", "context": "", "use_case": "", "switched_from": "", "story": "Krea 2 Technical Report"}, {"id": 770480225, "item_id": 48155014, "url": "https://news.ycombinator.com/item?id=48155014", "by": "vunderba", "date": "2026-05-15", "stance": "recommend", "quote": "or even older WAN could easily handle this", "excerpt": "Local text-to-vid such as LTX Video 2.3 or even older WAN could easily handle this then combine with something like SeedVR2 to upscale. https://github.com/Lightricks/ComfyUI-LTXVideo", "context": "", "use_case": "", "switched_from": "", "story": "Cut Off: why access to frontier AI will soon be scarce and selective"}, {"id": 762990663, "item_id": 47686916, "url": "https://news.ycombinator.com/item?id=47686916", "by": "jabrotapu", "date": "2026-04-08", "stance": "neutral", "quote": "Vision and video diffusion models: Flux, Wan 2.1, Stable Diffusion", "excerpt": "Location: Ahmedabad, Gujarat, India Remote: YES Willing to relocate: No Technologies: TypeScript, JavaScript, Python Node.js, Express, Nest, Next.js, GraphQL, React Native, Microservices, WebSockets React SQL and NoSQL databases LLM agents with LangGraph, LangChain, and RAG pipelines Self-hosted AI infrastructure: Ollama, Open WebUI, AnythingLLM, ComfyUI Vision and video diffusion models: Flux, Wan 2.1, Stable Diffus", "context": "Full-stack engineer seeking remote role", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (April 2026)"}, {"id": 760218337, "item_id": 47513646, "url": "https://news.ycombinator.com/item?id=47513646", "by": "EugeneOZ", "date": "2026-03-24", "stance": "recommend", "quote": "There are open-source alternatives:", "excerpt": "There are open-source alternatives: https://mochi1ai.com/ https://wan.video/ and others. There are free to use tools also.", "context": "", "use_case": "", "switched_from": "", "story": "OpenAI set to discontinue Sora video platform"}, {"id": 751873314, "item_id": 46992082, "url": "https://news.ycombinator.com/item?id=46992082", "by": "bleuradience", "date": "2026-02-12", "stance": "neutral", "quote": "video gen via Wan 2.2", "excerpt": "BleuNova AI Agent \u2013 a personal, self-hosted agent built from scratch with a focus on ethics and security. Core constraints I set for myself: No cloud dependency by default (Ollama/local models first) Immutable ethical rules enforced at runtime (truthfulness, harm prevention, consent, audit logging) Zero-trust execution (Docker sandboxing, network isolation, timeouts) Continual learning without catastrophic forgetting", "context": "", "use_case": "", "switched_from": "", "story": "BleuNova \u2013 Ethical self-hosted AI agent (privacy-first)"}, {"id": 737912576, "item_id": 46119536, "url": "https://news.ycombinator.com/item?id=46119536", "by": "Maxious", "date": "2025-12-02", "stance": "neutral", "quote": "This generation was run on an RTX 3060 (12 GB VRAM)", "excerpt": "Wan 2.2: \"This generation was run on an RTX 3060 (12 GB VRAM) and took 900 seconds to complete at 840 \u00d7 420 resolution, producing 81 frames.\" https://www.nextdiffusion.ai/tutorials/how-to-run-wan22-image-to-video-gguf-models-in-comfyui-low-vram", "context": "", "use_case": "Local video generation", "switched_from": "", "story": "Apple Releases Open Weights Video Model"}, {"id": 737859586, "item_id": 46116224, "url": "https://news.ycombinator.com/item?id=46116224", "by": "culi", "date": "2025-12-01", "stance": "compare", "quote": "WAN is only behind Google's Veo in image-to-video rankings", "excerpt": "Qwen, Hunyuan, and WAN are three of the major competitors in the vision, text-to-image, and image-to-video spaces. They are quite competitive. Right now WAN is only behind Google's Veo in image-to-video rankings on llmarena for example https://lmarena.ai/leaderboard/image-to-video", "context": "", "use_case": "Image-to-video generation", "switched_from": "", "story": "DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]"}, {"id": 735577088, "item_id": 45973568, "url": "https://news.ycombinator.com/item?id=45973568", "by": "Uehreka", "date": "2025-11-18", "stance": "recommend", "quote": "I recently used WAN to generate a looping clip of clouds moving quickly", "excerpt": "I design projections for independent theatre in Baltimore. I use AI in my workflows where it can help me and won\u2019t compromise on the quality of what I\u2019m making. I frequently use AI to upscale crappy footage, to interpolate frames in existing video (for artistic purposes, never with documentary archival stuff) and very occasionally to create wholesale clips in situations where video models can do what I need. I recent", "context": "", "use_case": "", "switched_from": "", "story": "Blender 5.0"}]}