Fitness Routine Video with Consistent Character Identity
A four-scene image-to-video prompt depicting a woman in pink yoga pants performing a gym workout, from entry through stretching, exercise, and a confident mirror moment. It emphasizes facial identity consistency from a reference image, soft natural lighting, and a realistic cinematic fitness aesthetic.
Soulful Ai @soulful__ai
Prompt (original, unmodified)
Scene 1: She enters the gym with a calm, confident expression, adjusting her hair. She is wearing fitted pink yoga pants and a minimal, elegant workout top. Soft natural lighting, clean aesthetic gym interior. Scene 2: She performs warm-up stretches with controlled, graceful movements. Close-up shots must accurately match the facial features from the provided reference image (same face structure, skin tone, expressions, and identity consistency). The pink yoga pants subtly highlighted through motion. Scene 3: She transitions into workout exercises such as lifting light dumbbells or using a treadmill. Movements are smooth and realistic, with proper form. The outfit (pink yoga pants) enhances the visual flow without being distracting. Scene 4: She pauses, wipes sweat with a towel, and looks at herself in the mirror with a subtle confident smile. Soft glow lighting, cinematic finish, maintaining elegance and strength. Style: realistic, cinematic, soft lighting, high detail, professional fitness aesthetic Camera: mix of medium shots and close-ups, smooth transitions Mood: disciplined, calm, self-growth focused Character consistency: maintain exact facial features from reference image throughout all scenes Output: high quality, smooth motion, natural body proportions, no distortion
Reproduced verbatim from the original post. Never edited or translated. Everything outside this block is our own commentary.
How this prompt compares
The techniques this prompt uses are more common in sports prompts than in the library overall:
| Technique | In sports | Library average | Lift |
|---|---|---|---|
| tracking | 65% | 41% | 1.58x |
Across all 5,926 prompts, the techniques used here appear at: tracking 41%, close-up 40%, natural light 29%, wide shot 26%.
