Compare the Tsundere Stomp AI Trend references
These complete external source performances are credited for reference. They are not results made with your photos on this website.
Main room
The adult man with short dark hair, a black sweater, blue jeans and white socks in the plain grey room; the single full-body performer.
@einmann33 · external source reference · 10.4 seconds
Green sweater
The older-looking adult in a green sweatshirt and dark patterned trousers who steps back from the phone and stomps; the small white dog at floor level is not assigned.
@savanay_60 · external source reference · 7.5 seconds
Make your video from photos
Watch the full reference and review its actual length, framing and performer roles.
Choose Create my video and assign a clear photo to the single performer position.
Review the selected clip, background option and photo assignments, then sign in and create using one video credit.
Follow the task in My videos, review the full result, prepare its available reference audio and download the MP4.
Everything runs in your browser. There is no dance to learn or performance to record. Processing can take several minutes; check the existing task in My videos before submitting again.
Price and what your video includes
Each selected reference costs one video credit to personalize. Watching is free, and downloading a completed result is included. There is no subscription.
Discounted packs: Previously $9.90 $6.99 for 1 video, Previously $19.99 $16.99 for 3 videos, Previously $27.99 $24.99 for 5 videos. See Pricing for validity and purchase terms. A confirmed failed generation releases its credit; an uncertain task remains under review.
Generation is upgraded from 480p to a 720p request using Higgsfield Genjutsu Light. Credits never expire. The selected reference supplies its timing and original audio; completed downloads are MP4 files. Source preview resolution is not a guaranteed export resolution.
Choose your photo
Use one clear adult photo with the head, torso, arms and legs visible. The arm cross and raised knee need room to read. The main take maps the black-sweater adult; the green-sweater version maps the standing adult and leaves the small white dog unassigned. A shared group photo is unnecessary. In pet mode, a full-body animal photo makes the intended upright pose clearer, while paws and crossed limbs remain demanding.
Use JPG or PNG up to 10 MB. Select the reference first; changing it clears earlier photo assignments. Use your own pet or consenting adults.
Tsundere Stomp AI Trend origins
According to the source page read on 12 November 2026, a bunny sound posted by @theo60473 in October preceded the November dance wave. A Natsuki fan-animation edit helped attach the game character's name to the pout, while adult takes by @savanay_60, @einmann33 and others spread the routine. The page dates @savanay_60's take to 7 November and the main adult wave to 8 November. These are reported creator-post dates, not verified upload timestamps for the files hosted here.
Historical account and measurements: Source report.
Watch the performance
Play the complete source before assigning photos. Source dimensions describe the preview, not a guaranteed output format.
| Part | What to watch |
|---|---|
| Bounce | Stand square to the fixed camera with the whole body in frame. |
| Knee and stomp | Raise one knee and plant the foot; the movement should read before the crossed-arm pose. |
| Hmph turn | Cross the arms, lift the chin and turn away with an exaggerated sulk. |
| Repeat | The main take opens the arms and repeats the cross, kick and turn. |
| Green-sweater take | The earlier adult walks away from the phone, places hands at the hips and stomps while the dog watches. |
Casting and caption ideas
The contrast is the caption: someone normally serious doing a large, theatrical sulk. Use an adult friend who agreed, yourself or a pet in the existing pet mode. A message about waiting for a reply or being late for dinner fits the short routine. This workflow changes the requested performer appearance; it does not turn the photo into Natsuki or add an anime face filter.
Sound and sharing
Original audio from the selected tsundere take. The download prepares the audio actually present in the selected reference. It does not clone your voice or grant music rights. Check the posting platform’s music permissions and keep its required AI label.
The external preview is not evidence of a completed generation with your photo. Review the existing task before spending another credit; retry audio preparation on that task if needed.
Review the result
| Issue | What to check |
|---|---|
| The arms merge | Use an unobstructed standing photo and inspect the crossing movement in the full result. |
| The stomp is too subtle | Show the legs in the input photo and check the selected source's knee lift. |
| Black sweater or jeans carry over | Source clothing may influence the result; review it rather than assuming an exact wardrobe transfer. |
| The wrong take opens | Choose Main room or Green sweater before entering the studio and confirm the preview. |
| The small dog changes | Only the adult is assigned in the green-sweater take; the watching dog is not a second role. |
Tsundere Stomp AI Trend FAQ
Is the Natsuki stomp an anime filter?
The name refers to the pose and trend history. These templates use two full adult dance references and the existing motion-transfer workflow, without an anime-character conversion.
Which version is the main reference?
Main room uses @einmann33's 10.356009-second take. Green sweater keeps @savanay_60's separate 7.458333-second take. Both belong to this one canonical page.
Does switching versions keep the same video?
No. Each version has its own complete source file, soundtrack, timing and studio ID. Check the preview after switching.
Can I assign the dog in the earlier take?
No. The green-sweater reference assigns its adult lead; the small watching dog remains a background character.
Which hashtags fit the routine?
The source associates it with #tsundere, #natsuki, #hmph and the Russian #цундере. Use tags that describe your actual clip and retain the required AI label.
Is watching the preview free?
Yes. Watching is free. Creating a personalized video requires signing in and one video credit, including a two-role edit. See the current one-time packs on the pricing page.
What does the generator request?
The existing generator requests 720p and prepares an MP4 with the selected reference’s audio. It does not provide the source site’s model menu or guarantee every background, effect or clothing detail.
Where can I follow my video?
Use My videos in the same signed-in account. A confirmed failed generation releases its reserved credit; an uncertain task remains under review. No new paid generation is needed merely to retry a download.