Guide: https://vidmuse.ai/blog/The-ultimate-vidMuse-guide 

Your current balance: 4,210 credits

Estimated costs:

• Image generation (66 shots): ~924 credits
• Video generation (66 shots): ~2,086 credits
• Total estimated: ~3,010 credits

Remaining after completion: ~1,200 credits for 4 minutes 12 seconds

Two models:

• Studio Mode: Uses the flagship models. It delivers the best image quality and supreme detail.
• Lite Mode: Uses the Seed series models. It's fast and credit-efficient.

Aspect Ratio and Resolution

• Aspect Ratio: Choose between Landscape or Portrait.
• Resolution: VidMuse supports 1080p and 720p.
• we suggest using a 30s–60s clip to get the hang of it. 

Current Templates:

• Story MV: Narrative-driven music videos.
• Abstract MV: Visuals focused on mood and artistic expression.
• Performance MV: Focus on characters singing or dancing.
• Viral Short: Optimized for social media engagement.
• TVC: Commercials and advertisements.
• Explainer: Visual storytelling for information.

Upload Reference Images

You can upload images for your

• Characters
  • singers (Make sure every reference image contains exactly one person and clean backgrounds)
  • lead actors
  • supporting cast
• Styling
• Costumes
• Props like necklaces, journals, or tools.
• Scenes / Locations

Starting off

I created an R&B song called 'Love Like Water.' I want to express how close the distance is between love and dreams. I want the MV to include both acting and singing performance, along with many atmospheric shots (B-roll). Image 1 is my female lead. Image 2 is the performer (he does not sing). Image 3 is the outfit I want for the female lead.

Prompt 1

Cinematic music video focused on one man refined through pressure and fire. The artist himself is the central figure. He moves forward calmly through heat, smoke, and drifting embers without fear or panic. Fire represents refinement, not destruction. The tone is grounded, serious, controlled, and powerful.

The video begins with a close-up or medium shot of the artist singing with restrained emotion under firelight and shadow, then transitions into cinematic imagery. The video alternates between brief performance moments and symbolic visuals, returning to singing during chorus moments and at the end. Singing shots are minimal, calm, and intentional, using side angles, partial profiles, and shadows, with no exaggerated mouth movement.

Visual imagery includes walking through smoke, heat shimmer in the air, embers floating, fire reflecting off metal and stone, and signs of endurance and refinement.

Camera movement is slow and deliberate with cinematic push-ins or side tracking.

Lighting is dramatic and realistic with warm fire tones against deep shadows, film grain, volumetric lighting, shallow depth of field, high contrast shadows, and dramatic backlighting. The video ends calm, steady, and resolved, with fire softening instead of exploding.

The theme is pressure creates precision — fire refines.

Avoid cartoon or anime styles, fantasy armor, superheroes, glowing eyes, neon colors, exaggerated muscles, cheap AI visuals, shaky camera, fast cuts, explosions, chaos, overexposed fire, subtitles, or text overlays. Aspect ratio square or poster-safe framing. Motion strength low to medium. Pacing slow and cinematic. Camera shake off.

Prompt 2

Photorealistic intimate performance scene, quiet nighttime interior, dim warm lighting, soft shadows, empty room atmosphere, artist alone in the space, slow restrained movement, realistic human facial expressions, subtle emotional delivery, reflective and sorrowful tone, cinematic realism, no cartoon style, no exaggeration, minimal camera movement, shallow depth of field, Heartbreaking country ballad performance with NO SMILING always sad and longing and contemplating, deep regret and longing, restrained intensity, vulnerability without melodrama, soft mood, quiet desperation, emotional stillness, lived-in sadness Consistent wardrobe throughout entire video, artist wearing black cowboy hat, dark sunglasses, and black gloves at all times with no changes including face and hair length , no changes to artist appearance from uploaded photo , no removal, no flicker, no morphing, no accessory variation, artist appearance remains identical from start to finish including face and hair and hat and gloves no changes to any from the uploaded avatar and no smiling this is a serious song , Rain falling outside a dark window, reflections on glass, city or small-town lights blurred in the distance, artist standing still, contemplative posture, quiet sorrow, cinematic and realistic , stillness and silence, sense of absence, cinematic realism, Keep as Many Lip Sync Avatar Moments as Possible. realism and high detail, soft focus on the background elements. NO wide Strange Joker Type Smiles Mouth remains consistent sad normal while lip syncing as well as hair and face stays the same throughout along with cowboy hat sunglasses and gloves again NO WIDE smile like the joker from batman nothing that even resembles a smile. and please stay within the alotted budget

Prompt 3

Prompt 4

Please reference the style and atmosphere of https://www.youtube.com/watch?v=u8LrJdPp7vQ, regenerate the TVC ad for Perrier Carbonated Mineral Water, in the summer of Paris. Use Perrier’s brand colors: signature green and yellow, consistent with the provided images. All visuals should reinforce this distinctive palette.

Prompt 5

Prompt 6 

做一个mv，A high-fashion MV storyboard featuring a girl with a black bob haircut. Style: Neo-Retro Futurism. She wears sleek, pure white modular mecha parts mixed with flowing technical silk. The environment is a clean, bright urban utopia with glass architecture. Lighting is soft, airy, and diffused, featuring delicate iridescent light leaks and prism effects. Avoid dark neon/grunge. Colors: Ivory white, matte silver, pale blue, and subtle holographic accents. Minimalist, futuristic, aesthetic, sharp focus, 8k cinematic shot.

Prompt 7

A 14-year-old girl named Sarah with pale skin, messy shoulder-length black hair with choppy bangs, large expressive hazel eyes with dark circles underneath, a small upturned nose, thin lips, and a slender build is positioned on the left side of a wide, dimly lit school hallway. She wears a faded navy blue oversized school sweater over a white collared shirt, a dark grey pleated skirt, and worn-out black leather school shoes. Her head is bowed in a posture of disgrace, with faint red marks visible on her cheek. In the background, out of focus, a group of three teenagers aged 15 to 17 stand by a row of green metal lockers, their bodies turned away but their heads tilted back in mocking laughter. The lighting is cool and oppressive, provided by flickering fluorescent ceiling panels that cast long, distorted shadows on the scuffed linoleum floor. Through a small rectangular window of a heavy wooden door, the silhouettes of a rock band are visible in a darkened room, their faces obscured by deep shadows and the glare on the glass. The air is thick with a somber, greyish atmosphere characteristic of a Studio Ghibli aesthetic, emphasizing a sense of isolation and internal fear.

Prompt 8

为这首歌的前 1:15 秒生成一个 MV，类似Vogue杂志的动态大片。画面背景是极简的高饱和度纯色（亮黄、洋红）。主角穿着oversize的亮面漆皮外套，戴着墨镜，面无表情地对着镜头打响指。随着鼓点（beat）的敲击，画面出现故障艺术（Glitch Art）的撕裂效果，色彩在黑白与红蓝之间剧烈切换。 * **关键词（Prompt Elements）：** > High-end fashion editorial video, Vogue style, pop art vibrant colors, solid studio background, confident fashion model, slick leather texture, glitch art effects, chromatic aberration, rhythmic flashing strobe lights, "snap" gesture, sharp focus, dynamic camera angles, MTV style music video.

Music Analysis Summary:

• Key: G Minor (serious, stoic, grounded emotion)
• BPM: 71 (deliberate, heavy—like a hammer on an anvil)
• Duration: 4 minutes 12 seconds (~252s)
• Structure: Classic verse-chorus with an extended climax (168s–226s) building to intense emotional peaks, then cooling down in the outro
• Energy: Alternates between low-energy verses (the struggle/raw material) and high-energy choruses (fire/transformation), perfectly mirroring your "refinement through fire" theme

The music's dynamic contrast and deliberate pacing will work beautifully with alternating performance and symbolic visuals.

Lyrics Extracted:

The lyrics are now ready on the canvas for you to review. If you'd like to adjust any of the transcribed lines, just let me know and I can refine them.

Style Selection / Customization

Based on your inputs, VidMuse suggests initial styles. You can select one or describe your preferred style in the chat (e.g., "Cyberpunk," "Vintage 90s," "Watercolor"). If you aren't satisfied, keep refining the request—VidMuse will adapt!

examples:

• Wong Kar-wai Style Cinematic MV

Selected Style: "Deakins-esque Atmospheric Cinema"

This style is inspired by legendary cinematographer Roger Deakins, known for his mastery of natural and practical lighting, high contrast shadows, volumetric atmosphere, and grounded realism. It perfectly matches your vision of dramatic firelight, film grain, and cinematic composition.

Creative Summary

VidMuse will generate a Creative Brief—think of this as the "Director’s Script." It defines the plot, visual style, and overall pacing of your project.

Project Overview

• Mode
• Project Title
• Theme
• Tone
• Pacing
• Traget Audience
• Primary Rhythm Driver
• Estimated Duration
• One-Sence Summary

Reference Images

You can upload images for your

• Characters
  • singers (Make sure every reference image contains exactly one person and clean backgrounds)
  • lead actors
  • supporting cast
• Styling
• Costumes
• Props like necklaces, journals, or tools.
• Scenes / Locations

Scene and Shot List 

(No credit consumption)

• Scene: Breaks the MV into narrative sections (different environments/moods).
• Shot List: Specific camera directions.
  • Start Frame: The visual look.
  • Action & Camera: Movement guidance.
  • Shot Type: Normal (Acting/Cinematography) or Avatar (Lip-syncing focus).
  • Duration: How long the shot lasts.
  • End Frame: The closing state of the shot.

Storyboard

(High credit consumption)!!!!

VidMuse now uses image generation models to visualize every shot.

Generate Videos

Once the Storyboard looks perfect, it's time to animate!