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
Reimagine the subject of this painting in a realistic style photo, generate a close-up medium shot portrait of her against a bright blue sky with white puffy clouds, stylized with a modern, fashion-influenced aesthetic. The subject, a woman, wears a light-grey t-shirt with print that reads "AICREATORS.TOOLS" in purple and lime colors with rainbow paint splashes around. On her head she wears a dark-grey baseball cap with silver details. Her long blonde hair falls freely from underneath the cap. Her expression is cheeky and flirtatious, gazing directly at the camera with a light smirk and a playful wink. She holds a little dog in her hands. The lighting is natural and bright, creating a high-contrast image against the vibrant sky, rendered with sharp focus and natural color tones. Tall format, realistic style
Like some other models, Wan 2.5 loses character reference when going form painting to realistic, even after tweaking the prompt to say more clearly 'Reimagine the subject of THIS painting'.
This subject presented as a premium collectible figurine on a designer’s desk. Scene: • Center: a realistic 1/6-scale figurine of the subject on a clear round stand, natural museum pose one foot slightly forward. Keep their current outfit, hair, and accessories exactly as in the source. • Right: an upright glossy retail box showing the same subject as box art matching outfit and look, with brand AI Creators Tools and model Gina; clean typography and a small authenticity sticker. • Left: a widescreen monitor displaying the subject as a grayscale digital sculpt/turntable in a 3D app UI that clearly matches the figurine. • Desk props: keyboard, mouse pad, a couple of notes; tidy and minimal. Lighting & look: • Bright natural studio daylight from windows, soft shadows, subtle tabletop reflections. • Photoreal materials hair, crisp print on the box, no duplicates or mismatches between figure, box, and monitor. Style tags: photoreal, product photography, studio lighting, sharp focus, clean composition
Three small childlike creatures stand before a quiet suburban house at night, viewed through a dim, doorbell camera lens. Each has a carved jack-o-lantern for a head, glowing with flickering fire inside as thin trails of smoke rise into the cold air. They tilt their heads sideways in eerie unison, their tattered vintage clothes hanging loosely. The left one holding large saw. They begin a slow, stop-motion zombie-like, robotic synchronized stomping. Overhead, a large bat flutters by erratically, its wings casting jittery shadows across the frame. The scene glows with a muted orange and greenish hue, flickering like an old VHS recording. The middle one opens mouth even wider and lets out a gnarly, distorted laugh — half robotic, half demonic. Camera pushes in on the exaggeratedly largely opens mouth and into it, in a dramatic motion, inside the burning mouth looks like a scary monster's one, dark slimy large sharp teeth and bluish-pink tongue, camera flying through it into the throat landing in the darkness.
Ultra-realistic cinematic scene of a rugged adventurer woman running through collapsing ancient jungle ruins. The wavy-haired redhead woman is dressed in a weathered explorer outfit — a khaki fedora hat, dirt-streaked lilac shirt with rolled-up sleeves, distressed dust-orange cargo pants. She sprints forward through a dark stone corridor. Massive crumbling pillars, dust clouds, and falling debris fill the air. Dynamic handheld chase cam tracks her from a low side angle, weaving between wreckage, capturing a sense of chaos and motion, intercut with rapid cuts and a close-up of her intense face from the front. Motion blur and camera shake emphasize speed and danger. Dramatic lighting with shafts of sunlight piercing through cracks in the ceiling, illuminating dust and rubble. Dynamic composition, cinematic depth of field, high detail, volumetric lighting, photoreal textures, cinematic color grading.
Wan2.5 doesn't really do jump cuts? Judging form 3 different prompts and ~7 generations. The character will turn around and run a different direction if a prompt calls to see them from another angle.
{ "shot": { "composition": "Medium close-up of couple at café table, rack focus to background pedestrian", "camera_motion": "Static hold with subtle rack focus transition", "frame_rate": "24fps", "film_grain": "Fine, cinematic grain" }, "subject": { "description": "A couple sitting at a Parisian café, hands entwined across a table", "wardrobe": "The man in a casual blazer with an open collar shirt, the woman in a light summer dress" }, "scene": { "location": "Sidewalk Parisian café with white iron chairs and striped awnings", "time_of_day": "Late afternoon, golden sunlight", "environment": "Bustling yet serene street with tree shade, pedestrians strolling" }, "visual_details": { "action": "Couple shares an intimate gaze, rack focus reveals a shocked man in background", "props": "Small bouquet of yellow and purple flowers, suitcase by the background man" }, "cinematography": { "lighting": "Warm natural sunlight with gentle shadows from trees", "tone": "Romantic and serene, shifting subtly to unsettling tension" }, "audio": { "ambient": "Soft murmur of street life, faint clinking of cutlery, indistinct footsteps", "avoid": "No intrusive loud traffic, no modern background music" }, "color_palette": "Warm yellows, soft greens, muted blues with subtle contrast", "dialogue": { "character": "woman", "line": "He’s in New York till Friday, darling.", "character": "man", "line": "So I can have you all to myself.", "subtitles": false, "captions": false, "show_subtitles": false, "show_captions": false, "text_overlay": false, "disable_text": true } }
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 speeding lime-green with black details SUV barrels through a congested city street under harsh midday sunlight, the camera tracking low and fast along its side as it swerves out of control.
The shot whips upward in a dramatic crane move just as it violently collides at speed with an old looming gas tanker, making a dent and triggering an explosion and a colossal fireball that engulfs the block in roaring flames. Shards of glass and chunks of debris streak past the lens, filling the frame with blistering chaos. The impact reverberates through the street, nearby vehicles jolting from the shockwave. The camera then pulls high into an aerial view, revealing the burning wreckage and frantic motion of the chaotic scene below.
Static camera captures a whimsical scene as a stylish cat, wearing sunglasses, mustard top, and silver hat dances on stage. He does a cheeky head toss to flip his hair, as if he’s in a music video. Then starts lightly stomping and does rhythmic nodding with a smug smirk, like he knows he owns the stage. He dances confidently to a groovy beat, exuding cool attitude and charisma. Ends a sequence by leaning back slightly, one paw stretched high, frozen in a triumphant finishing stance. The vibrant neon sign in the background reading 'AI Creators Tools rocks!' glows warmly, casting a playful light on the feline star.
Generated on September 30, 2025:
An example of dance movements prompting in Wan 2.5, for a cat - naturally.
This is a nice motion copy but if you notice the odd lines/streaks sometimes flashing - those are artifacts coming from woman's hair in motion in the driving video. The driving video had 2 girls dancing.
This is the 4th variation of the prompt wording but Wan 2.2 keeps 'cheating' and literally turning the city into a bubble-wrapped mini-Earth! In other generations it'd do a "circular mask transition" or "iris wipe (reverse)" transition. Doesn't help that the max prompt length is smaller than for 2.1.
Another example form Wan, where it's rather slow motion than bullet time but it's quite fun to watch. The woman is like 'I'm going to enjoy this vacation if it kills me!'
No matter how hard I tried to prompt for the man to be unhappy about the woman's advances, he just wouldn't refuse the kiss fromt his charming XXL lady.
Wan 2.1 14b quantized image to video 480p Q4_K_S gguf. Online version censors this image and won't generate anything wit it. No double dolly visible here anyway.
Prompt:
Surreal scene of a delicately ornate porcelain mug with an embossed gold floral pattern along the rim and upper edges, featuring a highly realistic…
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 October 7, 2025 at 3:42 AM
