Alibaba’s Wan team is hosting its open-source AI video tool online, offering easy access to people who can't or don't want to host the free model locally. Wan is a powerful model often leading the VBench leaderboard, outperforming both open-source and commercial competitors.
We are listing this platform separately for clarity purposes, if you're looking for a free PC-based Wan, please check out this entry. Here we're highlishting what the online platform offers.
In August 2025 Wan adds their avatar lip sync tool. Wan2.2-S2V is a 14B model made for cinematic, audio-led human animation. It goes past simple talking heads and aims for pro quality used in movies, shows and web stuff. (It’s open-source too.) It keeps movement consistent across long videos. You can guide motion and background with clear instructions.
Educators and TrainersCreative ProfessionalsContent CreatorsMedia and Film MakersMarketing and Branding SpecialistsDevelopers and Tech CreatorsNonprofit and Advocacy CreatorsSmall Business OwnersEntertainment and Performance ArtistsProfessional Content Creators
The animation is great, except the bird on her head doesn't really wobble, which could add even more realism. Also, Wan zooms in and crops this one each time.
Bottom right corner - redraw man's arm holding the watch, specifically elbow area removing an artifact which looks like a bag or purse. In center-left, behind horse carriage and directly below boy's knee erase what looks like deformed horse part. Preserve all else intact.
Cheap tourist snapshot, handheld, slightly shaky and crooked angle, as if taken by an unskilled friend. A 30-year-old stylish blonde woman, mid-sentence, looking a little confused and caught off guard, her expression suspended between talking and posing. She’s standing dead center in front of a major tourist landmark, though the framing is awkward and cuts part of it off. Behind her, a random passer-by photobombs the shot — a young man suddenly leaping in from the left, frozen mid-air with a wild, unhinged expression and flailing arms, almost cartoonish. His exaggerated presence clashes with the woman’s seriousness. Lighting is flat, daytime overcast, emphasizing the raw, unpolished snapshot quality. Poor composition, random tourists half-cropped at the edges, and a sense of chaotic realism as if the camera captured a fleeting, messy, and hilarious moment.
Miniature dogs made entirely out of colored paper (labrador, poodle and husky) playing football on a field in urban settings on highly defined green grass field. One storefront reads "AIcreators.tools" it's got various flowers inside behind the glass windows and doors
Crescent Moon Sculpture with a town inside, made of quartz material, features autumn, with lights hanging from houses in the forest, creating a warm and cozy atmosphere. The warm lighting effect enhances the overall scene. The sculpture is set against a white background with a beautifully carved quartz base, showing exquisite details and bright colors, evoking a feeling of warmth and joy. 4k, high definition, clear, sharp, miniature.
An extreme closeup shot of a 30-year-old man with tan skin and messy dark hair falling over his face. He’s staring straight at the camera with cold light-blue eyes that kinda stop you. Strands of his hair catch the light and frame his look. There’s a clean tattoo on the side of his face running from cheek to temple. It’s got a bit of rough texture that stands out against his smooth skin. The lighting’s sharp and moody. It throws some parts in shadow while showing off the details in his skin and the wet bits of hair. The background’s a blur, keeping all focus on him. Shot with a telephoto lens and a shallow depth of field. The image’s super clear, pulling out every little thing - from the look in his eyes to the way his hair sits. The whole vibe feels raw, personal, and a little gritty.
@LunaCreator_87317 Está decorando un árbol de Navidad dentro de una acogedora sala de estar en miniatura, iluminada con calidez. Luces doradas navideñas brillan suavemente contra el papel pintado pastel, proyectando sombras acogedoras.
La cámara empieza con un primer plano de su mano colocando un adorno rojo y plateado de Papá Noel en una rama. El ambiente se siente íntimo, artesanal y festivo.
Luego se corta a un plano medio amplio, por encima del hombro, donde ella gira la cabeza hacia la cámara y dice suavemente, en un susurro, “Happy Holidays”.
Sin previo aviso, la cámara acelera violentamente hacia atrás, atravesando una diminuta ventana en un solo movimiento ininterrumpido.
La habitación se encoge rápidamente a medida que la cámara se aleja, revelando la estructura completa: una encantadora y detallada casa de muñecas enclavada en un espacio tranquilo, con un interior que brilla cálidamente mientras que el exterior se siente sereno y onírico. El marco final muestra una casa de muñecas en miniatura rodeada de nieve suave y luces navideñas borrosas. El exterior, de color verde pálido, está cubierto de nieve y una cálida luz brilla desde el interior.
En el centro del marco, una ventana abierta revela una acogedora sala de estar. La mujer de @LunaCreator_87317 se encuentra dentro, enmarcada por cortinas blancas, mirando al frente con una sonrisa amable. Detrás de ella, un árbol de Navidad iluminado con adornos rojos se encuentra junto a un sofá rojo y lámparas que brillan suavemente.
Detalles exteriores en miniatura (un pequeño árbol decorado, una mesa auxiliar con lámpara y un reloj de pared) se apoyan contra la casa mientras la nieve se acumula en la base. El fondo adquiere un efecto bokeh cremoso, que enfatiza la escala de la casa de muñecas y la calidez propia de un cuento de hadas. Se escuchan villancicos de fondo.
Generated on December 18, 2025:
Using my own 'role'. Reference video to video. Again, Spanish translation of prompt due to unwise censorship layer banning unknown innocent words. Background music sometimes doesn't get included, and if I add a second actor - a cat - that usually breaks the prompt, might be too complicated for that. But two actors work in principle
A delicate butterfly flutters into frame and lands on a purple flower left off center, captured in extreme macro detail, subtle dust particles float in the air. The soft focus highlights its fragile wings, shimmering under faint sunlight. Blurred backdrop is greyish. The camera holds on the flower, then performs a rack focus behind it — blurred forms sharpen into view: heavy tank barrels rolling forward, dust kicking up, soldiers’ legs rushing past as shouts echo through the street. The camera then pulls back into a wide shot, revealing the full war-torn street - rubble, smoke, and fire engulfing the scene. The peaceful flower and butterfly contrasted against the chaos behind. A poetic, cinematic vibe underscores the fragile beauty against destruction.
A couple sits at a small white iron table outside café. They hold hands and look at each other. The shot stays steady with a light film-like grain. It starts focused on the couple, then shifts to the back. the woman says, “He’s in New York till Friday, darling.” The man in blue shirt who is sitting at the table says, “So I can have you all to myself.” Meanshile silent man with a suitcase slowly walks into view, rack focus shifting to his shocked face. That changes the mood fast. The street has striped awnings, café chairs, and a busy but quiet flow of people. You hear street sounds, some footsteps, and soft clinks of dishes. No traffic noise or music.
Tweaked JSON worked, otherwise there was some confusion. Multi-character dialogue is correct, focus shift works. Man's expression a bit too hilarious))
This multishot worked almost perfectly. Had to translate to Spanish because Wan's loopy censorship layer is triggered by something in the English variant.
Ok so with 'Smart Multi-shot' OFF it still works form a prompt alone and 'No talking' instruction is followed - great! Not as dynamic a video as it could be & face/skin looks plastic.
Seems like a chatty model, if you're not going to supply the lines, it'll say its own thing. This is 'Smart Multi-shot' (Inspiration Mode) on. Unfortunately seems like multi-shot and prompt enhance are baked together, so unchecking it removes both madeup text and camera cuts?
This was fun. But had to tweak the prompt a bit to prevent text to detach from packaging. Smaller font still does for a short while. This is sound-driven gen, speech by ElevenLabs.
Wan 2.6 is out. You can now drop characters from other videos into fresh scenes.
It builds full stories from short prompts. These can run up to 15 seconds in HD with synced sound and visuals.
Image generation got an upgrade. You can use text and images together to make stuff like posters or charts.
model
September 24, 2025
Wan2.5-Preview is now out.
It runs on a native multimodal design that works across text, images, video and audio. It can generate videos with synced audio covering vocals, sound effects and background music. It can follow directions more clearly to produce photorealistic results, varied art styles, imaginative text effects and pro-level charts.
model
August 27, 2025
Avatar lip sync model Wan2.2-S2V-14B is out and available for use on the platform.
model
May 17, 2025
Five days left to take advantage of Wan's online platform membership sake (till May 23). Get 50% off plus 1 month free if you sign up for yearly plan, which starts as low as $60.
promo
Useful Links
No additional links available for this tool.
This page was last updated on December 18, 2025 at 7:39 AM
