About this template
Style: - Starting from the provided image, the woman in the parka is taking a slow sip of coffee, steam gently rising from the mug. As she sips, the camera slowly pushes in closer to her face, capturing the subtle tension around her eyes. She lifts her gaze directly to the viewer
Style: - Starting from the provided image, the woman in the parka is taking a slow sip of coffee, steam gently
Built on Wan 3.0, this template turns a single frame into fluid motion — the AI generates the movement, lighting and camera work automatically.
The prompt behind this template
Style: - Starting from the provided image, the woman in the parka is taking a slow sip of coffee, steam gently rising from the mug. As she sips, the camera slowly pushes in closer to her face, capturing the subtle tension around her eyes. She lifts her gaze directly to the viewer, her expression shifting to frustration, and speaks in a strained, annoyed voice, "Why am I always in a coffee shop?" Then, she deliberately lowers the hood of her parka, revealing more of her face, and continues, "You could have drawn me on a beach sipping a margarita, but nooo! It has to be coffee!". She shakes her head once, a small, decisive movement, and looks back down at her coffee cup, then mutters with exasperation, "Man., you could have at least spiked it with Bourbon or something, " while the ambient sound of low, distant coffee shop chatter and the soft whir of an espresso machine underscore her monologue.
Copy this prompt into the custom generator to remix every detail.
Prompt breakdown for Style: - Starting From The Provided Image
These are exact phrases from the editable source prompt, grouped by the part of the result they control.
- Subject
the woman in the parka is taking a slow sip of coffee
"Man
- Scene and setting
"You could have drawn me on a beach sipping a margarita
- Camera and composition
the camera slowly pushes in closer to her face
How to use Style: - Starting From The Provided Image
- Open the template — no uploads needed, the prompt does the work.
- Tap Generate and let the AI do the work.
- Preview, download in full resolution, or regenerate with tweaks.
Template details
- AI model
- Wan 3.0
- Output
- Video
- Cost per generation
- 1,110 credits
- Typical wait
- 2-4 min
- Clip length
- 5s video
Frequently asked questions
Which words control the Subject in Style: - Starting From The Provided Image?
This prompt uses “the woman in the parka is taking a slow sip of coffee”. Change this layer first and keep the remaining prompt stable while you compare results.
Which words control the Scene and setting in Style: - Starting From The Provided Image?
This prompt uses “"You could have drawn me on a beach sipping a margarita”. Change this layer first and keep the remaining prompt stable while you compare results.
Can AI turn a single picture into a Style: - Starting From The Provided Image video?
Yes — Wan 3.0 animates one still image into a moving clip, generating the motion, lighting and camera movement automatically. No video editing skills are needed.
Is Style: - Starting From The Provided Image censored or filtered?
No. XXXCut runs Wan 3.0 without mainstream content filters for verified adults 18+. All output is 100% AI-generated fictional content, and illegal material is strictly prohibited.
How long does it take to generate Style: - Starting From The Provided Image?
Most generations finish in about 2-4 min. Video templates take longer than images because the AI renders every frame of the clip.
Is Style: - Starting From The Provided Image free to try?
Yes — new accounts get free credits at signup plus daily check-in bonuses, enough to try Style: - Starting From The Provided Image for free. After that, each generation costs 1110 credits.
