{"id":1557,"date":"2026-03-18T22:41:01","date_gmt":"2026-03-18T22:41:01","guid":{"rendered":"https:\/\/wiro.ai\/blog\/?p=1557"},"modified":"2026-09-27T18:44:32","modified_gmt":"2026-09-27T18:44:32","slug":"seedance-pro-v1-5-8-prompts-for-text-to-video-and-image-to-video","status":"publish","type":"post","link":"https:\/\/wiro.ai\/blog\/seedance-pro-v1-5-8-prompts-for-text-to-video-and-image-to-video\/","title":{"rendered":"Seedance Pro v1.5: 8 Prompts for Text-to-Video and Image-to-Video"},"content":{"rendered":"<p><strong>Seedance Pro v1.5<\/strong> was tested here as a short-form video tool, not as a demo reel generator. The eight prompts ask a practical question: can one model keep a clear subject, a readable camera instruction, and believable motion inside a five-second clip? Six tests start from text. Two start from an image, where the job changes from inventing a shot to preserving a composition while adding motion.<\/p>\n<nav aria-label=\"Table of contents\">\n<ul>\n<li><a href=\"#test\">What this test checks<\/a><\/li>\n<li><a href=\"#settings\">Parameters and output details<\/a><\/li>\n<li><a href=\"#results\">Eight output notes<\/a><\/li>\n<li><a href=\"#pick\">When to pick this model<\/a><\/li>\n<\/ul>\n<\/nav>\n<h2 id=\"test\">What the Seedance Pro v1.5 test checks<\/h2>\n<p>Each text-to-video prompt names a subject, a visible action, a camera move, and a lighting or material cue. That makes failures easier to spot. A good product clip needs a stable watch and a coherent orbit. A food clip needs steam, hands, grill action, and focus changes without turning the frame into noise. The city, robot, reef, and hangar prompts add scale, repeated detail, stylization, or several moving elements.<\/p>\n<p>The two image-to-video tests are deliberately quieter. The marathon asks for runners and flags to move while the camera tracks forward. The lagoon asks for waves, palm leaves, and a slow aerial drift. They test whether an input image remains recognizable when motion is introduced. Those are different jobs, so they should not be judged by the same standard as a fully generated scene.<\/p>\n<p>The model page on Wiro is <a href=\"https:\/\/wiro.ai\/models\/bytedance\/seedance-pro-v1-5\">Seedance Pro v1.5<\/a>. ByteDance describes the release as an audio-visual model with image-driven generation and complex camera movement support. These eight runs intentionally disabled audio so the visual result stays the subject of the comparison.<\/p>\n<h2 id=\"settings\">Parameters and what Wiro reports<\/h2>\n<ul>\n<li>Duration: 5 seconds<\/li>\n<li>Resolution: 480p<\/li>\n<li>Aspect ratio: 16:9<\/li>\n<li>Audio generation: false<\/li>\n<li>Watermark: false<\/li>\n<li>Seed: -1, so every run uses a random seed<\/li>\n<\/ul>\n<p>The model documentation exposes 480p, 720p, and 1080p choices, several aspect ratios, optional first and last images, audio, watermark, seed, and a fixed-camera option. This set used the documented 480p option and the existing post&#8217;s 16:9 setting. It did not record a fixed-camera value, so no claim is made about that parameter.<\/p>\n<p>Neither the Wiro model documentation nor the saved post records a per-output run time or price for these eight outputs. No number is inferred here. Treat elapsed time and cost as values to check in the Wiro run details for a new job, especially when changing duration, resolution, or audio.<\/p>\n<h2 id=\"results\">What each output shows<\/h2>\n<h3>1. Product orbit: a constrained studio shot<\/h3>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-01-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-01.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 1. Prompt: Studio product shot of a stainless steel wristwatch on a matte black pedestal. Slow camera orbit from left to right. Softbox reflections sweep across the metal. Shallow depth of field. Clean dark background.<\/figcaption><\/figure>\n<p>This output puts the smallest number of variables on screen: one watch, one pedestal, one orbit. It is the most useful check for product work because any wobble in the watch face, band, or reflection is easy to see. The clip shows why a single camera instruction works well for a five-second product beat. It is suited to a cutaway, a landing-page hero, or a short ad insert rather than a full product explainer.<\/p>\n<h3>2. Street food: motion plus focus direction<\/h3>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-02-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-02.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 2. Prompt: Night street food stall under warm hanging bulbs. Steam rises from a hot grill as hands flip skewers. Handheld close-up push in, then rack focus to a tray of spices. Neon reflections on wet pavement.<\/figcaption><\/figure>\n<p>The second clip combines hand action, steam, wet reflections, and a focus target. That makes it a useful realism test. The output is best read as a sensory close-up: the grill and skewers supply the main action while steam and neon provide atmosphere. For repeatable work, keep the action hierarchy this clear. Asking for several unrelated events in five seconds makes it harder to tell whether a missed detail is a model issue or a crowded brief.<\/p>\n<h3>3. Miniature city: scale and repeated detail<\/h3>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-03-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-03.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 3. Prompt: Miniature diorama city at sunrise with tiny cars and trains. Tilt shift look. Slow top-down to three-quarter camera move. Sun rays through light fog. Crisp micro details.<\/figcaption><\/figure>\n<p>The city test asks for many tiny objects and a move from top-down to three-quarter view. It shows the appeal of using a designed miniature world rather than a literal aerial city: the tilt-shift treatment gives the clip a strong visual rule. It is a better fit for an establishing shot, a game concept, or a stylized transition than for footage that must withstand close inspection of every vehicle and building.<\/p>\n<h3>4. Clay robot: style must carry the motion<\/h3>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-04-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-04.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 4. Prompt: Stop motion style clay robot in a pastel workshop. The robot waves, then assembles a paper airplane. Slightly jittery frame timing. Warm desk lamp lighting. Shallow depth of field.<\/figcaption><\/figure>\n<p>This is the strongest kind of stylized test because the requested jitter helps the medium rather than hiding mistakes. The output has a readable sequence: wave first, paper airplane second. That sequencing matters. Use this model for playful character inserts when the action can be divided into one or two beats. For a precise assembly tutorial, shoot or animate the hands separately; the prompt asks the model to infer too much fine manipulation.<\/p>\n<h3>5. Reef drift: group motion without a hero subject<\/h3>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-05-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-05.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 5. Prompt: Underwater coral reef scene with sun beams from the surface. A school of small fish turns as one. Slow forward dolly. Floating particles. Natural colors, cinematic contrast.<\/figcaption><\/figure>\n<p>The reef output tests a broad environment where the main movement belongs to a group of fish rather than a single character. It works as an atmospheric drift shot because the slow dolly gives the scene one direction. This is a sensible use case for generative video: a brief scene-setting moment where water, particles, light beams, and a school turning together create the point of the shot.<\/p>\n<h3>6. Hangar docking: scale, lights, and background activity<\/h3>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-06-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-06.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 6. Prompt: Sci fi spaceship docking sequence inside a large hangar bay. Blue guidance lights pulse along the walls. Slow wide shot with subtle camera shake. Sparks from a welding arm in the background.<\/figcaption><\/figure>\n<p>This output is a controlled complexity test. The ship, pulsing guidance lights, welding sparks, and a large room all compete for attention. The wide shot keeps the request legible because it prioritizes scale over small mechanical detail. It fits concept trailers and sci-fi transitions. Do not use a short model-generated clip as evidence of an exact docking procedure or continuity across a long sequence.<\/p>\n<h3>7. Marathon image-to-video: preserve the starting frame<\/h3>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1408\" height=\"768\" class=\"wp-image-1538\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-01.jpg\" alt=\"Seedance Pro v1.5 marathon input image for image-to-video test\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-01.jpg 1408w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-01-510x278.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-01-900x491.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-01-768x419.jpg 768w\" sizes=\"auto, (max-width: 1408px) 100vw, 1408px\" \/><figcaption>Input image for output 7.<\/figcaption><\/figure>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-07-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-07.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 7. Prompt: Animate the runners and flags with realistic motion. Smooth low angle tracking shot forward. Keep faces natural and avoid distortions. Bright morning light and clear sky.<\/figcaption><\/figure>\n<p>The marathon pair makes comparison simple: the still supplies the crowd, bridge, and daylight composition; the output adds runner and flag movement plus a tracking move. This is the better workflow when a campaign already has an approved key visual. Ask for modest motion first. A crowded frame leaves less room for face-level precision than a single-subject shot.<\/p>\n<h3>8. Lagoon image-to-video: small motion, stable composition<\/h3>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1408\" height=\"768\" class=\"wp-image-1539\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-02.jpg\" alt=\"Seedance Pro v1.5 tropical lagoon input image for image-to-video test\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-02.jpg 1408w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-02-510x278.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-02-900x491.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-input-02-768x419.jpg 768w\" sizes=\"auto, (max-width: 1408px) 100vw, 1408px\" \/><figcaption>Input image for output 8.<\/figcaption><\/figure>\n<figure><video controls preload=\"metadata\" poster=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-08-poster.jpg\"><source src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/03\/seedance-08.mp4\" type=\"video\/mp4\" \/><\/video><figcaption>Output 8. Prompt: Animate gentle waves and palm leaves moving in a light breeze. Slow aerial drift forward over the lagoon. Bright midday sun with sparkling highlights on water.<\/figcaption><\/figure>\n<p>The lagoon run is the cleanest image-to-video brief in the set. Waves, leaves, sunlight, and a forward drift all reinforce the starting composition instead of changing it. Pick this approach for travel imagery, property mood clips, and social loops where visual consistency matters more than plot.<\/p>\n<h2 id=\"pick\">When to pick Seedance Pro v1.5<\/h2>\n<p>Pick Seedance Pro v1.5 when a short clip needs one clear visual idea, a named camera move, and either a text-led scene or gentle animation from an existing image. The model supports audio generation, but audio was disabled in this test; enable it only when sound is part of the brief and assess it in its own pass. For image-led work, use a stable source image and ask for restrained motion. For text-led work, keep one main action and one camera instruction.<\/p>\n<p>For more video-testing context, see <a href=\"https:\/\/wiro.ai\/blog\/ltx-video-vs-kling-vs-seedance\/\">LTX-Video vs Kling vs Seedance<\/a>, <a href=\"https:\/\/wiro.ai\/blog\/cinematic-image-to-video-models\/\">Best Cinematic Image-to-Video Models<\/a>, and <a href=\"https:\/\/wiro.ai\/blog\/top-5-text-to-video-apis-in-2026-1-prompt-each\/\">Top 5 Text-to-Video APIs in 2026<\/a>.<\/p>\n<h2>Official references<\/h2>\n<ul>\n<li><a href=\"https:\/\/seed.bytedance.com\/en\/seedance1_5_pro\" target=\"_blank\" rel=\"noopener\">ByteDance Seedance 1.5 Pro model page<\/a><\/li>\n<li><a href=\"https:\/\/seed.bytedance.com\/en\/blog\/sound-and-vision-all-in-one-take-the-official-release-of-seedance-1-5-pro\" target=\"_blank\" rel=\"noopener\">ByteDance Seedance 1.5 Pro release announcement<\/a><\/li>\n<\/ul>\n<h2>Run Seedance Pro v1.5<\/h2>\n<p><a href=\"https:\/\/wiro.ai\/models\/bytedance\/seedance-pro-v1-5\">Run Seedance Pro v1.5 on Wiro<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Seedance Pro v1.5 was tested here as a short-form video tool, not as a demo reel generator. The eight prompts ask a&hellip;<\/p>\n","protected":false},"author":4,"featured_media":1556,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55],"tags":[133,57],"class_list":["post-1557","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-prompt-guides","tag-seedance","tag-text-to-video"],"_links":{"self":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/1557","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/comments?post=1557"}],"version-history":[{"count":2,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/1557\/revisions"}],"predecessor-version":[{"id":4214,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/1557\/revisions\/4214"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/media\/1556"}],"wp:attachment":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/media?parent=1557"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/categories?post=1557"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/tags?post=1557"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}