#wan2gp
Hydraulic Press Crushing Toy Cake made with Wan2GP and MMAudio. Full tutorial on youtube. No cakes were harmed in the making of this video. #asmr #hydraulicpress #wan2gp #aivideogeneration #opensourceai #wan22 #mmaudio
August 18, 2025 at 5:19 AM
Hydraulic Press Crushing Gummy Bear made with Wan2GP + Wan 2.2 5B model + Crush It LoRA from Ostris. Full tutorial on youtube - youtu.be/7xr_bylR_lo #wan2gp #aivideogeneration #ostris #hydraulicpress #opensourceai #wan2
August 16, 2025 at 12:42 AM
Alibaba's Wan2.1 GP

Generates a 8s WAN 480P video (14B model non quantized) with only 12 GB of VRAM or reduced the VRAM consumption of Wan2.1 by a factor of 2.

github.com/deepbeepmeep...
GitHub - deepbeepmeep/Wan2GP: Wan 2.1 for the GPU Poor
Wan 2.1 for the GPU Poor. Contribute to deepbeepmeep/Wan2GP development by creating an account on GitHub.
github.com
March 5, 2025 at 5:50 AM
Hydraulic Press Crushing Wedding Cake made with Wan2GP and MMAudio. Full tutorial on youtube. No cakes or weddings were harmed in the making of this video. #asmr #hydraulicpress #wan2gp #aivideogeneration #opensourceai #wan22 #mmaudio
August 22, 2025 at 5:01 AM
◆wan2gp

元々はFlasherで、AS2で一生メシ食えるつもりだったのは
20年前までw

現在のPJで、フロント側でアニメーション演出作ってるの聞いて、
久々に僕もFlash的なキーフレームアニメ作って見ようかと、
wan2gpっていうAI動画精製UIを、
StabilityMatrix様で環境構築してみた。

いや、クオリティ凄いよw でもね
【Adobe Animateで作ったほうが30倍くらい時短です】

長すぎるよ、生成時間がw
クロック3Ghzの物理32コア64スレ+RTX12GB版で、
フルHDの3秒の動画生成に20分掛かる。

こりゃ使い物にならんわ
July 2, 2026 at 11:08 PM
最近WAN2GP導入しました。最初全く動かんから諦めようと思ってたんだけど、Copilot先生のアドバイスのお陰で無事動くようになりましたので早速生成してみました。
WebUIで元画像を生成、その画像を元にWAN2GPで動画生成と言う流れです。
本当はComfyUIなら単体で出来る事みたいだけど何だかUIに馴染めなくて…。
あと、試しに日本語のpromptで生成してみました。(出来ると思ってなかった)

#AI動画 #Stablediffusion #WAN2GP
January 5, 2026 at 5:45 PM
I even learned Krita as an alternative to Photoshop and have been experimenting a bit with page design.

But the one thing I will not do is draw.

That will be the job of Confyu, Wan2GP, Grok, ChatGPT, and all those folks.

That’s where I draw the line.

Pun intended.+
July 18, 2026 at 5:40 PM
#Wan2GP #SCAIL-2 で生成。
OpenPoseを使わない処理らしいので破綻が少なそうう🤗

足上げるポーズもバッチグー👍
複数人とか難しかったエム字開脚も行けそう❤
August 9, 2026 at 11:24 PM
Домашняя ИИ-студия теперь в кармане Обновили WanGP —

приложение с открытым кодом для генерации видео, картинок и звука на своём ПК. Теперь можно запустить задачу дома, а с телефона смотреть результат и добавлять новые в очередь. Промпты диктуешь...

https://github.com/deepbeepmeep/Wan2GP
September 23, 2026 at 5:18 AM
😁 Thanks, in wan2gp with model wan 2.2,
December 11, 2025 at 1:40 PM
i stopped using Grok and Gemini and all long time ago because of the censorship but now i use open source models locally in my PC to create videos! plus it is free! you can explore Comfyui or Wan2GP to create such videos! the only issue is they're much slower depending upon your machine hardware!
September 19, 2026 at 9:48 AM
😱Long AI videos with consistent characters... for free?!
🎬 Created with InfiniteTalk in Wan2GP
🤓 Learn it in a few minutes ➡️ youtu.be/MVgIIcLtTOA
#AItools #InfiniteTalk #Wan2GP #OpenSourceAI #Veo3Alternative #aivideogeneration #nanobanana
September 12, 2025 at 4:49 PM
Wan2GP — это полноценная локальная видеостудия! Генерируйте видео и фото из текста без облака, подписок и лимитов. Работает даже на 6ГБ ОЗУ прямо в браузере. Поддержка LoRA, масок и топовых моделей. #Wan2GP #AIvideo #VideoGeneration #OpenSource #MachineLearning https://dappcrypto.org/r/kG
September 5, 2026 at 7:27 PM
Learn how AI image generation works from a polar bear in less than 1 minute #stablediffusion #aianimation #learnai #multitalk #wan2gp
July 25, 2025 at 4:57 PM
📝 Summary:

Open Generative AI is a free, open-source, self-hosted AI image/video studio offering 200+ models, no content filters, and modular studios (Image, Video, Lip Sync, Cinema, Workflow, etc.) with both local (sd.cpp or Wan2GP) and remote (Wan2GP server) inference, plus a hosted web (1/2)
June 27, 2026 at 2:16 PM
For TTS there's Namigen (Mac) on its way.

For the lip-sync stuff there's a solution for Windows:

MultiTalk Wan2GP (1.3GB model)

But even if ported to Mac and highly performant it's maybe still too limited to use it on a Mac with 10 GB VRAM: maybe we get 480px, 25/s?.
July 19, 2025 at 8:35 PM
Yeah, this one was animated on my Monster Box. Using Wan2GP, a fork of Wan2.1. I was using the full 16 bit text decoder and full 16 bit 14B parameter model.
May 5, 2025 at 6:14 PM
Labubu vs Hydraulic Press 🐰🙃
No actual labubus were harmed 😅
Made with open-source AI 🤓
Full tutorial ➡️ youtu.be/7xr_bylR_lo #labubu #HydraulicPress #AIVideogeneration #OpenSourceAI #WAN2GP #wan22
September 15, 2025 at 6:05 PM
No bears were harmed in making this video. Testing out new sound effect open source model HunyuanVideo-Foley. Full tutorial at youtu.be/7xr_bylR_lo. #asmr #hydraulicpress #wan2gp #aivideogeneration #opensourceai #wan22 #hunyuanvideo #foley
August 29, 2025 at 6:25 PM
Nah, mostly server.
This one is from Civitai.
720p's are from rented A40 server.
Local runs somehow give better results than Civitai, yet with low RAM it basically blocks your laptop for an hour. Framepack in that sense is even worse than quantized Wan2GP.
May 17, 2025 at 12:45 AM
画像生成AIの統合環境!
#StabilityMatrix がアップデートしてました。

最新版 #StableDiffusion #ForgeNeo を
実際にインストールして検証
結果、見事にやらかしました💦
✔ インストール手順
✔ やらかしポイント
1024x1024で2秒早くなりました👇
note.com/umanikomi/n/...
#画像生成AI #生成AI
StabilityMatrix 2.15.5(Wan2GP,StableDiffusion WebUI Forge-Neo)|umanikomi
いつの間にかStabilityMatrixがバージョンアップしていました(2025/12/28) そして、新たらしく ・StableDiffusion WebUI Forge-Neo ・Wan2GP が追加されて、Wan2.1/2.2の動画作成、QwenなどでもStabilityMatrixを利用できるようになりました! いろいろな画像生成を一括で管理してくれて、インストールも簡単、非常に便...
note.com
February 3, 2026 at 5:29 PM
If y'all enjoy #ai fun, install #wan2gp right this instant and play around with #minimax #h3. It's so good.
August 11, 2026 at 6:00 AM
github.com/deepbeepmeep...
github.com/leejet/stabl...
github.com/daniandthewe...
(一番下はsd.cppのWEB GUI)
忘れられがちだけどビデオ生成向けUIは結構ある(全てMinimax H3対応済)
GitHub - deepbeepmeep/Wan2GP: A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.
A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux. - deepbeepmeep/Wan2GP
github.com
August 4, 2026 at 10:22 PM