Video yükleniyor...
Video Yüklenemedi
Wan2.6: Commercial-Grade Image Output Wan2.6-Image is now available. 🖼️ Interleaved Text-and-Image Output:Generate interleaved text-and-image content with logical reasoning capabilities — enabling layered, narrative-driven visual storytelling. 🖼️ Multi-Image Conditioned Generation:Support flexible referencing, combining, and replacement of multiple images, integrating varied visual inspirations to generate novel and compelling results 🖼️ Commercial-Grade... show more
33,335 görüntüleme • 10 ay önce •via X (Twitter)
14 Yorum

Wan 2.6 is bad at prompt adherence, Btw it kinda sucks Wan changing completely it's position of King of Open Source to a Closed Source like OpenAi and Google You guys could release wan 2.5 weights, some of the community kinda feels betrayed right now

Wan 2.6 is poor at prompt adherence please update, specially camera position and angle.

got me automating tasks while wan2.6 turns me into an art director 😌

Explored @Alibaba_Wan it's working really well!

interleaving text and image in one generation stream is the workflow fix we needed.

It's not just a demo—it's an evolution that directly connects to actual production. 「デモ止まり」ではなく、実制作に直結する進化ですね。

why make new when you can just borrow from Qwen and stuff

Sure

Thank you for this blessing ❤️

Great release ,multi‑image conditioning and precise camera control sound like game‑changers for creators.

Idk the images still loOk so plastic 🙃

能把价格打下来么😭

Generate interleaved text and image outputs; avoid simple single-image generation.

Wan2.6 looks like a total game-changer! 🔥 Interleaved text-and-image storytelling, creative flexibility, and precise control over camera angles and lighting? Perfect for creating commercial-grade visuals with ease. Can’t wait to try this out!


