{"schema":"kovapi.model-page/1","model":"seedance-2.5-flash","family":["seedance-2.5-flash"],"name":"Seedance 2.5 Flash","page":"https://kovapi.com/en/model/seedance-2.5-flash","markdown":"https://kovapi.com/en/model/seedance-2.5-flash.md","docs":"https://kovapi.com/en/docs/seedance-2.5-flash","updated":"2026-11-19","endpoint":{"submit":"POST https://kovapi.com/v1/videos/generations","poll":"GET https://kovapi.com/v1/videos/jobs/{id}","async":true,"submit_status":202,"result":"data[0].url"},"params":{"model":{"type":"string","enum":["seedance-2.5-flash"]},"prompt":{"type":"string","max_chars":11000},"duration":{"type":"integer","min":4,"max":30,"unit":"second","alias":"seconds"},"resolution":{"type":"string","enum":["480P","720P"],"default":"720P"},"size":{"type":"string","enum":["16:9","9:16","1:1","4:3","3:4"],"alias":"aspect_ratio"},"images":{"type":"array","items":"https URL","max":10,"role":"reference: address them as @Image1, @Image2 ... in the prompt"},"video_references":{"type":"array","items":{"url":"https URL","duration":"read from the file"},"max":5,"total_seconds_max":30,"billed":true},"audio_reference":{"type":"array","items":"https URL","max":5,"billed":false},"callback_url":{"type":"string","note":"webhook when the job ends"}},"modes":[{"mode":"t2v","title":"Text to video","send":"Only prompt and the settings, no references.","get":"Picture, motion and sound from the text; write dialogue, effects and music into the prompt.","limits":"Only the general limits (see the specs)."},{"mode":"multi_ref","title":"Multi-image reference to video","send":"images in order; the prompt says what each image is for: a person, a product, a set, a style, a storyboard or a key frame.","get":"New footage that follows the references' look, framing or storyboard; several characters can appear together.","limits":"Up to 10 images, 300-6000 px a side, aspect 0.4-2.5. Every image is a reference, never a first frame."},{"mode":"video_ref","title":"Reference video to video","send":"video_references with video links (images may come too); the prompt says whether to follow the motion, the camera, the pacing or a blockout.","get":"The reference's motion and camera with new characters, sets and style; a 3D blockout can be rendered into finished footage.","limits":"Up to 5 videos, 30 s in total; reference-video seconds are billed (see pricing)."},{"mode":"audio_ref","title":"Reference audio","send":"audio_reference with audio links plus a reference image or video; the prompt says whether to follow the voice, the lines or the music.","get":"A character speaks new lines in the reference voice, or the picture follows the reference music's rhythm.","limits":"Up to 5 clips, not billed; must come with a reference image or video."}],"pricing":{"currency":"USD","unit":"second","tiers":{"480P":{"usd_per_second":"$0.06","official_usd_per_second":"$0.0672","save":"10%","ref_usd_per_second":"$0.035","ref_official_usd_per_second":"$0.0413","ref_save":"15%"},"720P":{"usd_per_second":"$0.12","official_usd_per_second":"$0.1512","save":"20%","ref_usd_per_second":"$0.07","ref_official_usd_per_second":"$0.0929","ref_save":"24%"}},"billed_seconds":"output seconds; with a reference video, reference-video seconds + output seconds at ref_usd_per_second","notes":["Without a reference video: the per-second rate of the resolution x output seconds. Reference images and audio are free. Example: 720P for 10 s = 10 x $0.12.","With a reference video: (reference-video seconds + output seconds) x the \"with reference video\" rate; every reference video counts. Example: a 10 s 720P clip with a 6 s reference = 16 x $0.07.","The price is held at submit and refunded in full if the job fails; automatic retries of one job settle once."]},"retention_days":7,"limits":["No 1080P, no first / last frame, no video editing or extension: for 1080P use Seedance 2.5, for a first or last frame use Wan 3.0.","Reference audio cannot be used alone; send it with a reference image or video. All three kinds can go together, each numbered: the second image is @Image2, the first audio clip @Audio1.","With a reference video and a prompt that changes that video (a new style, a re-render), the model may treat the job as a video edit, and the clip then keeps the reference video's ratio and length.","prompt is capped at 11,000 characters; Chinese and English count the same, punctuation, spaces and line breaks included.","Every clip has a soundtrack. To leave out music or voices write \"no background music\" or \"no dialogue\" in the prompt; \"no subtitles\" works too.","Photos of real people work as references; the likeness or voice of public figures and celebrities is refused by content review, and a refused job is not billed. Make sure you have the right to use the likeness."],"examples":[{"id":"kv-robot30","title":"Guardian robot: a nine-panel storyboard shot as 30 seconds","mode":"multi_ref","source":"kovapi","official_no":null,"params":{"duration":30,"resolution":"720P","size":"16:9"},"cost":"$3.60","video":"https://img.kovapi.com/i/mp-4308bb84eb3bff4b6c0e2f69.mp4","poster":"https://img.kovapi.com/i/mp-6068b32cc22d414a13cb0d2d.webp","prompt":"image1: 九宫格分镜参考，用于整体镜头结构、景别与运镜节奏。\nimage2: 火箭发射场黄昏草原实拍参考，用于环境构图、暖金夕照与冷暮蓝的写实彩色实拍质感基准。\nimage3: 主体 1 (守护机器人) 角色外观参考。\nimage4: 主体 2 (老奶奶) 角色外观参考。\n【主体设定】\n主体 1 (守护机器人): 参考 image3，近未来做旧复古机器人，做旧蓝绿色金属机身、斑驳锈蚀，圆顶头，两只发光的红色圆形机眼，细天线，细长关节四肢；体型高大，约为人类两倍高。\n主体 2 (老奶奶): 参考 image4，瘦小年迈女性，银发挽成低髻，皱纹深刻，身穿明黄金色及地长裙、缀金蓝刺绣胸襟，神情不舍；身高只及机器人胸口。\n环境 (黄昏草原・发射场): 参考 image2，近未来黄昏草原，暮色天空由暖金渐入冷蓝，远处地平线一座发射台矗立白色火箭、蒸汽升腾；及膝野草随风起伏，广袤空旷。\n【整体风格】\n真人实拍彩色电影正片，写实照片级质感，全程真实彩色画面；彩色 35mm 电影胶片质感，细腻真实胶片颗粒，浓郁饱满的电影级调色，IMAX 大画幅质感；手持摄影，呼吸感摇晃，浅景深大光圈，前景持续飘散的草叶、火星与灰烬，微微倾斜荷兰角，暖金夕照与冷暮蓝、爆炸暖橙强烈对撞，16:9 横屏。近未来温情灾难片氛围，静谧、悲壮、守护与不舍。\n【严格排除】黑白、单色、灰度、去色；手绘、素描、线稿、插画、漫画、动画；分镜稿 / 故事板、草图；移轴微缩、玩偶感、塑料 CG、油腻过曝 CG。\n【分镜头】(9 镜 ≈ 30s)\n镜头 1 (0-3s): 超远景低机位仰视，黄昏草原两人背影仰望远方火箭。台词 (机器人): \"I'm right here. I won't let go.\"\n镜头 2 (3-6s): 正面中景手持，机器人搀扶老奶奶。\n镜头 3 (6-10s): 面部特写，老奶奶眼含不舍。台词 (老奶奶): \"Fly safe, my child. Come back to me.\"\n镜头 4 (10-14s): 超远景仰摇，火箭升空拖曳浓白烟迹。台词 (老奶奶): \"There he goes... there he goes.\"\n镜头 5 (14-18s): 超远景，火箭在半空爆炸碎裂。台词 (老奶奶): \"No... no, no—\"\n镜头 6 (18-22s): 面部大特写，老奶奶瞳孔骤缩泪滑落。台词 (老奶奶): \"...he was almost there.\"\n镜头 7 (22-25s): 特写转近景，老奶奶崩溃痛哭。台词 (老奶奶): \"Bring him back! Please— bring him back!\"\n镜头 8 (25-28s): 超低视角近乎垂直仰拍，机器人环抱老奶奶罩成保护穹顶。台词 (机器人): \"Don't look up. I've got you.\"\n镜头 9 (28-30s): 超远景背影，两人紧紧相拥剪影。台词 (机器人): \"I'm still here. I'll stay... as long as you need.\"","inputs":{"images":["https://img.kovapi.com/i/mp-467106a4c8d7cb83c354cc07.png","https://img.kovapi.com/i/mp-cf25b8d66e978ef5855cda31.png","https://img.kovapi.com/i/mp-d8e099cda9738ccccfa1bb5a.png","https://img.kovapi.com/i/mp-e01a7bd8d09d396d64099c9b.png"],"video_references":[],"audio_reference":[]}},{"id":"kv-tire","title":"Tyre ad: a product photo plus three text cards","mode":"multi_ref","source":"kovapi","official_no":null,"params":{"duration":16,"resolution":"720P","size":"3:4"},"cost":"$1.92","video":"https://img.kovapi.com/i/mp-2dcaacdcc4f2451c5f1b45aa.mp4","poster":"https://img.kovapi.com/i/mp-79406926a9967e1dddf903b8.webp","prompt":"为图1中的商品生成视频，由中国中年自然肤色黑色寸头日常户外风男模特出镜，手持商品进行动态展示与解说。镜头 1，镜头从中景缓慢推进至近景。阳光明媚的广阔户外公路旁，一位中国中年、自然肤色、黑色寸头、穿着日常户外冲锋衣的男模特，一手扶着立在地上的大品牌轮胎，面向镜头自信地进行解说。 男主播：“大品牌轮胎，伴你安心出行。” 背景音乐：节奏轻快的户外运动风纯音乐。 画面正下方显示粗体黑字“大品牌轮胎 伴你安心出行” 参考图2。镜头 2，镜头特写轮胎正面花纹。男模特的手指顺着轮胎上深深的纵向排水沟槽滑动，随后手掌有力地拍打胎面，动态展示轮胎清晰的纹理和扎实的质感。 男主播：“强效排水，稳健抓地。” 背景音乐持续，伴随轻微的摩擦音效。 画面左侧弹出黑体大字“强效排水 稳健抓地” 参考图3。镜头 3，镜头平移转至轮胎侧面特写。男模特用手掌按压轮胎侧壁展示其优良的韧性与弹性，随后手指指向侧面凸起的品牌标识区域。 男主播：“静音舒适，坚韧耐用。” 背景音乐持续。 画面右侧弹出黑体大字“静音舒适 坚韧耐用” 参考图4。镜头 4，镜头拉远回到中景。男模特双手扶住轮胎边缘，轻松地将其向前滚动半圈，随后站定，微笑着向镜头竖起大拇指，背景是充满活力的自然风光。 画外音：“你的安心之选。” 音乐高潮处有力收尾。 画面中央浮现黑体大字“伴你安心出行” 参考图2","inputs":{"images":["https://img.kovapi.com/i/mp-6d18a3f328848a8401c1d37c.png","https://img.kovapi.com/i/mp-e80747cc976af420c832baff.png","https://img.kovapi.com/i/mp-b7de1cac42d0cf89e63906d7.png","https://img.kovapi.com/i/mp-5b00ca03b6560e4b93f7390f.png"],"video_references":[],"audio_reference":[]}},{"id":"kv-pixel","title":"Pixel martial arts: six key frames in one take","mode":"multi_ref","source":"kovapi","official_no":null,"params":{"duration":15,"resolution":"720P","size":"9:16"},"cost":"$1.80","video":"https://img.kovapi.com/i/mp-2ee2d1750be8ebe3789d15e6.mp4","poster":"https://img.kovapi.com/i/mp-7ab8440471821e57860d5bfe.webp","prompt":"根据 @图片1 - @图片6 制作一镜到底的像素武侠主题竖版视频，背景音乐使用国风 8bit 武侠风格音乐。全片统一浅蓝底色，像素风格统一，画面干净通透。\n镜头 1：静止展示 @图片 1 的「江湖风云」水墨风格 logo，背景为统一浅蓝底色，画面保持约 1 秒静止。\n镜头 2：@图片 1 中的文字区域消失后，@图片 2 的武侠男性角色像素脸部特写从画面底部滑入；角色眨眨眼看向镜头，随后快速向下位移离场；角色离场后，原本 logo 处变为 @图片 3 的蓝色「武功秘籍」像素书。\n镜头 3：紧接 @图片 4，像素武侠小人角色从画面下方用力向上跃出，顶起上方的蓝色菱形问号标，问号标上方弹出深蓝色粗体字「今日闯江湖！」；角色落地后摆出 @图片 4 的站姿 pose，随后抬手打招呼，接着做出预备跑动作，转身向画面右侧奔跑（奔跑姿态参考 @图片 5），镜头跟随角色向右移动，角色从画面右侧跳出画面。\n镜头 4：@图片 6 的 UI 界面从画面右侧位移入画，像素武侠角色从画面右上角跳入，落在「三月廿七日」大字的右下方，张开双臂摆出热情展示的定格姿势，最终定格在该画面。\n整体像素武侠美术风格，色调统一浅蓝底，运镜连贯顺滑呈现一镜到底的连续位移与跟随，元素过渡自然、角色动作衔接流畅，画面无卡顿、无闪烁；文字与 UI 清晰稳定。","inputs":{"images":["https://img.kovapi.com/i/mp-a8e6cafd16699c88bc205bde.png","https://img.kovapi.com/i/mp-d6a179f9802cc2abf2a287ff.png","https://img.kovapi.com/i/mp-c83b76a690b59f2c21e6ff58.png","https://img.kovapi.com/i/mp-5a28f9e51d489941e140610e.png","https://img.kovapi.com/i/mp-92c37e2d346d6d6316d76c50.png","https://img.kovapi.com/i/mp-7e7ee924787da67dc9b2d086.png"],"video_references":[],"audio_reference":[]}},{"id":"kv-family","title":"A family drama with six characters and two sets","mode":"multi_ref","source":"kovapi","official_no":null,"params":{"duration":15,"resolution":"720P","size":"9:16"},"cost":"$1.80","video":"https://img.kovapi.com/i/mp-33fa6ecbde27d0321307a8da.mp4","poster":"https://img.kovapi.com/i/mp-a3096410f3e401caf2391588.webp","prompt":"【统一风格与约束】 真实材质质感，细腻光影；角色面部和身体比例稳定，肢体结构自然，动作连贯，不僵硬，无穿模，无卡顿，无扭曲肢体，动作符合现实物理逻辑；禁止生成同款分身、双胞胎效果，同一画面中仅保留单个对应角色，不出现角色重复复刻；无字幕，无水印，无 logo，无乱码，无无关文字；无多余背景音乐。\n【参考素材】 将图片 1 中的角色定义为秦秀莲； 将图片 3 中的角色定义为刘春香； 将图片 2 中的角色定义为王强； 将图片 4 中的角色定义为小乐； 将图片 5 中的角色定义为小石头； 将图片 6 中的角色定义为二妞； 将图片 7 定义为县城火车站售票处的参考场景； 将图片 8 定义为刘春香家卧室的参考场景； 将纸质车票定义为去大城的火车票。\n镜头 1｜0 秒 - 2 秒\n以人物为中心构图，近景，平视，正面机位，日、内，固定。 县城火车站售票处。 秦秀莲站在售票窗口前看向售票窗口。 秦秀莲说：“一张去大城的票。”\n镜头 2｜2 秒 - 4 秒\n局部构图，特写，平视，正面机位，日、内，固定。 县城火车站售票处。 秦秀莲握紧去羊城的火车票，低头看向车票目的地，嘴唇闭合。 秦秀莲（V.O.）说：“刘春香能做，我也能做。”\n镜头 3｜4 秒 - 5 秒\n三分法构图，中景，平视，斜 45 度侧面机位，夜、内，固定。 刘春香家卧室。 刘春香和王强坐在桌边清点当天收入。 刘春香看向桌上钱币，说：“七百多。”\n镜头 4｜5 秒 - 7 秒\n以人物为中心构图，近景，平视，正面机位，夜、内，固定。 刘春香家卧室。 王强看向桌上钱币，说：“比开业那天还多。”\n镜头 5｜7 秒 - 9 秒\n以人物为中心构图，近景，平视，正面机位，夜、内，固定。 刘春香家卧室。 小乐爬到刘春香身边，看向刘春香，说：“麻麻，我给你捶背！”\n镜头 6｜9 秒 - 10 秒\n以人物为中心构图，近景，平视，正面机位，夜、内，固定。 刘春香家卧室。 小石头看向刘春香，说：“我也来。”\n镜头 7｜10 秒 - 11 秒\n以人物为中心构图，近景，平视，正面机位，夜、内，固定。 刘春香家卧室。 二妞看向刘春香，说：“还有我！”\n镜头 8｜11 秒 - 13 秒\n对称构图，中景，平视，侧面机位，夜、内，固定。 刘春香家卧室。 小乐、小石头、二妞围着刘春香捶肩捶背。 刘春香悄悄握住王强的手，王强反握刘春香的手。","inputs":{"images":["https://img.kovapi.com/i/mp-a6792abed7676768d2215f17.png","https://img.kovapi.com/i/mp-3ffc1f8f1d6e10f72f30876f.png","https://img.kovapi.com/i/mp-a597f359b98b6c84afff0b6a.png","https://img.kovapi.com/i/mp-1aa87318ba2ffa0e33a2f6f8.png","https://img.kovapi.com/i/mp-3a469285e81f868bd933d15c.png","https://img.kovapi.com/i/mp-6e5a0b7277826cf522ebc9dd.png","https://img.kovapi.com/i/mp-17786d9e48b89fa348215003.png","https://img.kovapi.com/i/mp-2ad7ea9eb1362c79e24ea40f.png"],"video_references":[],"audio_reference":[]}},{"id":"kv-white30","title":"Blockout plus key frames: a 30-second 3D animation","mode":"video_ref","source":"kovapi","official_no":null,"params":{"duration":30,"resolution":"720P","size":"16:9"},"cost":"$4.20","video":"https://img.kovapi.com/i/mp-0bd41c39a5f1b407e060bb64.mp4","poster":"https://img.kovapi.com/i/mp-644765c45667871176786720.webp","prompt":"以白模参考视频 <video1> 作为整支视频唯一的运镜、镜头节奏、景别变化、主体运动轨迹和镜头调度参考，严格保持白模视频的镜头顺序、机位变化、运动方式和节奏，不改变镜头结构，不新增镜头，不改变主体运动逻辑。结合各阶段关键帧参考图，生成一部 30 秒电影级 3D 动画短片，整体风格梦幻、童话、温暖，具有儿童幻想色彩，角色外形与各阶段的关键帧保持一致，不要改变角色形象，人物表情情绪随场景变化而改变。\n0-3s（首帧参考 <2pic>）镜头由全景俯视缓缓推向地上的小女孩，小女孩坐在房间的地毯上玩飞机，小女孩起身左转，右手使劲一挥将手里的飞机放飞。\n3-5s（参考 <3pic>）飞机从左至右穿过房间悬挂的星星挂件，小女孩乘坐飞机进入幻想的天空。\n5-8s（参考 <4pic>）镜头继续侧跟，以小女孩为中心的环绕。\n8-10s（参考 <5pic>）镜头环绕到小女孩驾驶的飞机背面、飞机开始缓缓俯冲海面。\n10-19s（参考 <6pic>、参考 <7pic>）小女孩继续向海底游去，一条鳐鱼游过来入画。\n19-23s（参考 <8pic>）小女孩从时空裂缝冲出来到幻想宇宙。\n23-24s（参考 <9pic>）前景小女孩和星球开始前翻转并，逐渐幻化消失。\n24-28s（参考 <9pic>）俯视镜头持续推进，小女孩躺在地的毯上熟睡。\n28-30s（参考 <10pic>）镜头继续推进绘本，随后爸爸进入画面。\n整体要求：所有画面均参考对应关键帧，白模视频仅作为运镜、镜头运动和角色动画参考，不参考画面内容。最终输出 30 秒 16:9 横构图宽屏视频。","inputs":{"images":["https://img.kovapi.com/i/mp-634ba490a460e269825e6f90.png","https://img.kovapi.com/i/mp-a51be9eda6947454338b6143.png","https://img.kovapi.com/i/mp-df1d64f97bbc630b33231d4e.png","https://img.kovapi.com/i/mp-00aea6106ad6fd195fae19d7.png","https://img.kovapi.com/i/mp-5eebe1628e0218cd71078837.png","https://img.kovapi.com/i/mp-d51ce51f1486ca0898e35865.png","https://img.kovapi.com/i/mp-12cb5d92cda9c1480119a4ef.png","https://img.kovapi.com/i/mp-a3675d2996c5a522a748a49d.png","https://img.kovapi.com/i/mp-8fb79f42e2a9f97c2ccbe27c.png"],"video_references":[{"url":"https://img.kovapi.com/i/mp-c0ff18bf0ffcbccf66defe15.mp4","duration":30}],"audio_reference":[]}},{"id":"kv-raccoon","title":"Blockout render: a raccoon on the rooftop","mode":"video_ref","source":"kovapi","official_no":null,"params":{"duration":6,"resolution":"720P","size":"16:9"},"cost":"$0.84","video":"https://img.kovapi.com/i/mp-6b458c6948b4392a399a1899.mp4","poster":"https://img.kovapi.com/i/mp-b1373cb14efa92eec1c7c2b8.webp","prompt":"将视频 1 进行白模渲染，无 bgm，只生成环境音和动作音。\n渲染要求：背景为深蓝与紫色色调的夜晚赛博朋克都市，密集的摩天大楼，楼宇间是巨大的全息广告牌与霓虹灯光，数个飞行器在空中穿梭，闪着微弱的灯光，发出微弱的机械声响；人物为一个身着黑色夜行衣的小浣熊，身影为一道剪影，脚步小心翼翼；人物移动的地点是摩天大楼中的一栋楼的屋顶。","inputs":{"images":[],"video_references":[{"url":"https://img.kovapi.com/i/mp-d773723e2985efc81c3d5546.mp4","duration":6}],"audio_reference":[]}},{"id":"kv-voice","title":"Same character, same voice","mode":"audio_ref","source":"kovapi","official_no":null,"params":{"duration":8,"resolution":"720P","size":"16:9"},"cost":"$0.96","video":"https://img.kovapi.com/i/mp-2608623ba6e9e5b0616fcc4c.mp4","poster":"https://img.kovapi.com/i/mp-b6b39686d283dabc814dabc2.webp","prompt":"【素材】@图片1 是周婆婆的外观参考，全程佩戴同一副老花眼镜；@图片2 是山神殿场景参考；@音频1 是周婆婆的声音，台词的音色、语速和口音都参考它。\n【概述】古装悬疑奇幻真人电影风格，电影级写实质感。清晨，周婆婆站在山神殿门口，送别画面外的人。\n0-4 秒：中景，晨光从殿门斜照进来，周婆婆站在门槛边，朝画面外轻轻挥手。周婆婆台词（温和）：“山路滑，慢些走。”\n4-8 秒：近景，周婆婆扶了扶老花眼镜，望着远处的山，眼里带着笑意。周婆婆台词（叮嘱）：“到了山下，记得回来报个平安。”\n【贯穿全片】稳定、缓慢的镜头；暖色晨光，背景自然虚化；只保留人声、风声和远处的鸟鸣，不要背景音乐；画面不显示字幕和文字。","inputs":{"images":["https://img.kovapi.com/i/mp-f500ebb875a7096ed01fb75a.png","https://img.kovapi.com/i/mp-18de79cd058f658275db14c9.png"],"video_references":[],"audio_reference":["https://img.kovapi.com/i/mp-00fbaccfff70ed326c2996f2.mp3"]}},{"id":"kv-temple","title":"Mountain shrine: acting detail in a period ensemble","mode":"multi_ref","source":"kovapi","official_no":null,"params":{"duration":14,"resolution":"720P","size":"16:9"},"cost":"$1.68","video":"https://img.kovapi.com/i/mp-81a6f0d1b7a5db14b74dba34.mp4","poster":"https://img.kovapi.com/i/mp-0f1150a6a9e17da2134af060.webp","prompt":"【生成目标】 生成周婆婆在山神殿内走近林秀兰、反复确认她的面容并激动落泪的连续场景。古装悬疑奇幻真人电影风格，电影级写实质感。昏暗古朴的山神殿内有陈旧木梁、旧神龛、烛台和祭祀陈设，暖色烛火轻轻摇曳，空气中漂浮细小尘埃。\n【主体与关系】 全程只有林秀兰、周婆婆、春丫、石头四人。春丫与石头分别搀扶周婆婆左右两侧；林秀兰始终站在周婆婆前方。保持参考人物的脸型、年龄、发型、服装和身高关系。周婆婆始终佩戴同一副老花眼镜。\n【资产锁定】 周婆婆严格参考@[图片3] 。 林秀兰严格参考@[图片2]， 山神殿场景严格参考@[图片3] 。\n【事件脚本】\n0—4 秒：中景镜头围绕周婆婆缓慢向前推近。春丫与石头小心搀扶周婆婆起身，三人步履缓慢地走到林秀兰面前。周婆婆始终凝视林秀兰的脸；认出她后，脚步短暂停顿，嘴唇轻颤，双眼逐渐睁大，神情从震惊转为难以抑制的激动，仿佛见到等待多年的故人。林秀兰安静站立，困惑而警觉地回望她。结束时周婆婆在林秀兰面前站定，春丫和石头仍扶住她。\n4—9 秒：切至周婆婆与林秀兰的面部近景。周婆婆先颤抖着扶正眼镜，再用一只手短暂揉一次自己的眼睛；确认没有看错后，她才伸出双手，轻轻捏住林秀兰两侧脸颊，缓慢左右拨看，再轻轻揉捏和拉扯确认。动作依次发生，不同时抢拍。手指准确接触脸颊，不遮挡眼睛、鼻子和嘴部。林秀兰被捏得轻微嘟嘴，露出错愕不解的神情，身体下意识稍稍后仰，但不挣扎、不躲开。周婆婆动作急切失态，却始终轻柔。结束时两人面部清晰可见，林秀兰的五官与脸型保持完整。\n9—14 秒：镜头先切至周婆婆逐渐湿润的双眼，再平稳移至周婆婆与林秀兰的双人近景。周婆婆松开林秀兰的脸，双手轻微颤抖。周婆婆使用苍老沙哑、生涩蹩脚、带轻微异族口音但清晰可辨的普通话，周婆婆台词（难以置信）：“像……“\n周婆婆台词（声音发颤）：“太像了。“\n周婆婆台词（惊喜）：“终于等到你了，乡亲们有救了。“最后一个字说完时，泪水从周婆婆眼中涌出，画面停留在她含泪而欣慰的神情上。林秀兰、春丫和石头全程自然闭口，只用眼神和表情回应。\n【摄影与声音】 采用稳定、缓慢、克制的电影运镜。人物面部始终清晰，背景自然虚化；暖色烛光勾勒人物轮廓，幽暗山神殿保持空间层次。表演细腻真实，不过度夸张。 <烛火轻微燃烧声、衣料摩擦声和山神殿细微声响> 极轻的低沉弦乐铺底，不遮盖台词。 没有旁白，画面不显示字幕、文字或标牌。\n【保持一致】 保持四名角色的身份、数量、外貌、服装、身高关系、空间方位和视线方向连续。老花眼镜始终正确佩戴，不漂浮、不消失。搀扶、停步、揉眼、捏脸、松手和说话严格按顺序衔接。手部结构正常，手指与脸颊接触准确；捏脸过程中林秀兰不换脸，五官位置和脸部结构保持稳定。\n【排除内容】 排除卡通感、滑稽恶搞、现代物品、掌掴、推搡和粗暴动作；排除人物换脸、年龄或服装变化、身高突变、角色增减、空间位置跳变和动作顺序混乱；排除手掌穿模、多余手指、手指粘连、手部畸形、脸部塌陷、五官扭曲、眼镜漂浮或消失；排除错误人物发声、多人同时说话、重复台词、漏词、口型错位和声画不同步；排除快速剪辑、跳帧、剧烈抖动、画面闪烁、字幕、文字、标志和水印。","inputs":{"images":["https://img.kovapi.com/i/mp-18de79cd058f658275db14c9.png","https://img.kovapi.com/i/mp-68c995a3f3b8d3ed104fc022.png","https://img.kovapi.com/i/mp-f500ebb875a7096ed01fb75a.png","https://img.kovapi.com/i/mp-92aad676f9cac1923940bffb.png"],"video_references":[],"audio_reference":[]}},{"id":"kv-panda","title":"A panda cub rolls down a hill","mode":"t2v","source":"kovapi","official_no":null,"params":{"duration":8,"resolution":"720P","size":"16:9"},"cost":"$0.96","video":"https://img.kovapi.com/i/mp-7913126fdea63ecd512cdc21.mp4","poster":"https://img.kovapi.com/i/mp-cde92c3a7011d6ca488a4a89.webp","prompt":"写实自然纪录片风格，电影级真实光影，温暖的午后, 在森林草坡上, 一只圆滚滚的熊猫幼崽从坡上滚下来.\n\n熊猫黑白毛发蓬松真实，体型小而胖，动作笨拙可爱。场景为绿色森林斜坡，地面覆盖青草、苔藓、三叶草、泥土、小石块、枯枝和少量小黄花，虚化背景中有高大树干与树林。镜头为低机位中远景，轻微手持感，整体基本固定，始终保持熊猫在画面中。\n\n0s-3s：一只熊猫幼崽趴在绿色草坡上，身体圆滚滚, 它刚开始顺着斜坡慢慢侧滚，动作笨拙，草叶被身体轻轻压弯。微风拂过, 阳光从左上方穿过树林，形成斑驳光影。\n3s-8s：熊猫滚到画面右下方，动作逐渐停止，从侧躺变成趴卧。它的圆脸朝向镜头，前爪压在草地上，熊猫趴在前景草丛中，身体调整到舒服的姿势，头部小幅抬起又放低, 发出轻微哼唧声。\n\n低机位，轻微手持感，轻微跟随熊猫向右下方移动。景深自然，前景草叶轻微虚化，熊猫主体清晰，背景树林柔和虚化。自然环境音，风声、熊猫滚动时轻微柔软的扑通声, 整体温暖、真实、自然。","inputs":{"images":[],"video_references":[],"audio_reference":[]}}],"faq":[{"q":"What is Seedance 2.5 Flash?","a":"The video model ByteDance released in November 2026, the Flash version of Seedance 2.5. On KovAPI it is seedance-2.5-flash: text to video and generation from reference images, videos and audio, with sound, up to 30 s per clip."},{"q":"How much does Seedance 2.5 Flash cost per second, and for a 30-second video?","a":"720P $0.12/s and 480P $0.06/s, billed by output seconds. A 30-second 720P clip is $3.60; with a reference video you pay (reference seconds + output seconds) x $0.07 at 720P. The playground quotes each clip before you submit."},{"q":"Seedance 2.5 Flash vs Seedance 2.5: what is the difference, and which should I use?","a":"Same prompts and parameters (4-30 s, five ratios, image / video / audio references together, sound in every clip). Differences: Flash is 480P / 720P only, takes up to 10 images, 5 videos and 5 audio clips (2.5: 30 / 10 / 10), and costs less per second. In our same-prompt tests simple shots came out close, while with many key frames or lots of on-screen text 2.5 was more faithful. A common workflow: draft in Flash, finish in 2.5."},{"q":"Does it support 1080P?","a":"No. Seedance 2.5 Flash renders 480P and 720P only; 1080P is refused at submit with a 400 and nothing is charged. For 1080P use Seedance 2.5."},{"q":"How many reference images, videos and audio clips can one request take?","a":"10 images, 5 videos (30 s in total) and 5 audio clips, all usable together; more is refused at submit with a 400 and not charged."},{"q":"Reference to video vs image to video: can I set the opening frame?","a":"On this model every image is a reference: the people, products and sets in it appear in the video, but the first frame is not guaranteed to be that image. Writing \"open on the frame of @Image1\" gets close. If a picture must be the first frame, use Wan 3.0, which has first-frame mode."},{"q":"How is a reference video billed?","a":"(Reference-video seconds + output seconds) x the \"with reference video\" rate: 720P $0.07/s, 480P $0.035/s. Reference images and audio are free."},{"q":"How long does it take?","a":"In our November 2026 tests: about 2 minutes at 480P and 4-8 minutes at 720P (longer clips take longer), more at busy hours. While queued, read queue_position and eta_seconds; the job status is what counts."},{"q":"Can I use photos of real people?","a":"Yes, as references and without masking. The likeness or voice of public figures and celebrities is refused by content review, and refused jobs are not billed. Make sure you have the right to use the likeness."},{"q":"I asked for 16:9, so why did my clip with a reference video come back in another ratio?","a":"When the prompt changes the reference video itself (a new style, a re-render), the model may treat the job as a video edit, and the clip keeps the reference video's ratio and length. For a new ratio, write \"follow the camera of video 1 and make a new clip\", or use a reference video in the ratio you want."},{"q":"Does the video have sound? Can I turn it off?","a":"Every clip has a soundtrack with dialogue, effects and music generated with the picture; audio: false has no effect. To leave out music or voices, write \"no background music\" or \"no dialogue\" in the prompt."},{"q":"Am I charged if generation fails?","a":"Generation failed, not billed, resubmit as is. The hold placed at submit is refunded in full, and automatic retries of one job settle once."},{"q":"How long are videos kept?","a":"Clips and uploaded references are kept for 7 days and then deleted; download what you need."},{"q":"I already use seedance-2.5. What changes if I switch?","a":"Set model to seedance-2.5-flash; every other field is the same. Mind Flash's reference limits (10 images / 5 videos / 5 audio) and resolutions (no 1080P): anything over is refused at submit with a 400."}],"notes_for_ai":["The model id is seedance-2.5-flash; submit with POST /v1/videos/generations (HTTP 202 with the job id) and read results with GET /v1/videos/jobs/ plus the id.","resolution is 480P / 720P only, default 720P, no 1080P; size takes 16:9 / 9:16 / 1:1 / 4:3 / 3:4. seconds aliases duration, aspect_ratio aliases size.","Every image is a reference; there is no first / last frame and image_role has no effect on this model; name images in upload order as @Image1 and so on.","Reference limits: 10 images, 5 videos (30 s in total), 5 audio clips; audio must come with an image or a reference video.","audio: false has no effect; every clip has sound. prompt is capped at 11,000 characters. Reference images must be 300-6000 px a side with aspect 0.4-2.5, or the submit is refused with a 400 (not billed).","A job with a reference video is billed (reference seconds + output seconds) x the reference rate (720P $0.07/s); without one, output seconds x $0.12/s at 720P.","With a reference video and a prompt that changes that video, the clip may keep the reference video's ratio and length (the model treats it as an edit)."],"versus":[{"id":"vs-panda","title":"Text only: a panda cub rolls down a hill (8 s, 16:9)","params":{"duration":8,"size":"16:9"},"prompt":"写实自然纪录片风格，电影级真实光影，温暖的午后, 在森林草坡上, 一只圆滚滚的熊猫幼崽从坡上滚下来.\n\n熊猫黑白毛发蓬松真实，体型小而胖，动作笨拙可爱。场景为绿色森林斜坡，地面覆盖青草、苔藓、三叶草、泥土、小石块、枯枝和少量小黄花，虚化背景中有高大树干与树林。镜头为低机位中远景，轻微手持感，整体基本固定，始终保持熊猫在画面中。\n\n0s-3s：一只熊猫幼崽趴在绿色草坡上，身体圆滚滚, 它刚开始顺着斜坡慢慢侧滚，动作笨拙，草叶被身体轻轻压弯。微风拂过, 阳光从左上方穿过树林，形成斑驳光影。\n3s-8s：熊猫滚到画面右下方，动作逐渐停止，从侧躺变成趴卧。它的圆脸朝向镜头，前爪压在草地上，熊猫趴在前景草丛中，身体调整到舒服的姿势，头部小幅抬起又放低, 发出轻微哼唧声。\n\n低机位，轻微手持感，轻微跟随熊猫向右下方移动。景深自然，前景草叶轻微虚化，熊猫主体清晰，背景树林柔和虚化。自然环境音，风声、熊猫滚动时轻微柔软的扑通声, 整体温暖、真实、自然。","clips":[{"model":"seedance-2.5-flash","resolution":"720P","video":"https://img.kovapi.com/i/mp-7913126fdea63ecd512cdc21.mp4","cost":"$0.96","verdict":"Flash 720P: the roll, the sit-up and the look to camera are all there, at about three quarters of the 2.5 rate."},{"model":"seedance-2.5","resolution":"720P","video":"https://img.kovapi.com/i/mp-ed231c10ec7c24e490b6cceb.mp4","cost":"$1.264","verdict":"Seedance 2.5 720P: calmer motion, slightly more fur and light detail."},{"model":"seedance-2.5-flash","resolution":"480P","video":"https://img.kovapi.com/i/mp-845124c7cefabca29f45e306.mp4","cost":"$0.48","verdict":"Flash 480P: half the 720P price, good for drafts in bulk."}]},{"id":"vs-tire","title":"A talking product ad: one product photo plus three text cards (16 s, 3:4)","params":{"duration":16,"size":"3:4"},"prompt":"为图1中的商品生成视频，由中国中年自然肤色黑色寸头日常户外风男模特出镜，手持商品进行动态展示与解说。镜头 1，镜头从中景缓慢推进至近景。阳光明媚的广阔户外公路旁，一位中国中年、自然肤色、黑色寸头、穿着日常户外冲锋衣的男模特，一手扶着立在地上的大品牌轮胎，面向镜头自信地进行解说。 男主播：“大品牌轮胎，伴你安心出行。” 背景音乐：节奏轻快的户外运动风纯音乐。 画面正下方显示粗体黑字“大品牌轮胎 伴你安心出行” 参考图2。镜头 2，镜头特写轮胎正面花纹。男模特的手指顺着轮胎上深深的纵向排水沟槽滑动，随后手掌有力地拍打胎面，动态展示轮胎清晰的纹理和扎实的质感。 男主播：“强效排水，稳健抓地。” 背景音乐持续，伴随轻微的摩擦音效。 画面左侧弹出黑体大字“强效排水 稳健抓地” 参考图3。镜头 3，镜头平移转至轮胎侧面特写。男模特用手掌按压轮胎侧壁展示其优良的韧性与弹性，随后手指指向侧面凸起的品牌标识区域。 男主播：“静音舒适，坚韧耐用。” 背景音乐持续。 画面右侧弹出黑体大字“静音舒适 坚韧耐用” 参考图4。镜头 4，镜头拉远回到中景。男模特双手扶住轮胎边缘，轻松地将其向前滚动半圈，随后站定，微笑着向镜头竖起大拇指，背景是充满活力的自然风光。 画外音：“你的安心之选。” 音乐高潮处有力收尾。 画面中央浮现黑体大字“伴你安心出行” 参考图2","clips":[{"model":"seedance-2.5-flash","resolution":"720P","video":"https://img.kovapi.com/i/mp-2dcaacdcc4f2451c5f1b45aa.mp4","cost":"$1.92","verdict":"Flash: presenter, tyre and voice-over right; one vertical caption wrong."},{"model":"seedance-2.5","resolution":"720P","video":"https://img.kovapi.com/i/mp-87927e076c7f1080f771dab5.mp4","cost":"$2.528","verdict":"Seedance 2.5: all four captions right, cleaner layout."}]},{"id":"vs-pixel","title":"Six key frames in one take: pixel-art martial arts (15 s, 9:16)","params":{"duration":15,"size":"9:16"},"prompt":"根据 @图片1 - @图片6 制作一镜到底的像素武侠主题竖版视频，背景音乐使用国风 8bit 武侠风格音乐。全片统一浅蓝底色，像素风格统一，画面干净通透。\n镜头 1：静止展示 @图片 1 的「江湖风云」水墨风格 logo，背景为统一浅蓝底色，画面保持约 1 秒静止。\n镜头 2：@图片 1 中的文字区域消失后，@图片 2 的武侠男性角色像素脸部特写从画面底部滑入；角色眨眨眼看向镜头，随后快速向下位移离场；角色离场后，原本 logo 处变为 @图片 3 的蓝色「武功秘籍」像素书。\n镜头 3：紧接 @图片 4，像素武侠小人角色从画面下方用力向上跃出，顶起上方的蓝色菱形问号标，问号标上方弹出深蓝色粗体字「今日闯江湖！」；角色落地后摆出 @图片 4 的站姿 pose，随后抬手打招呼，接着做出预备跑动作，转身向画面右侧奔跑（奔跑姿态参考 @图片 5），镜头跟随角色向右移动，角色从画面右侧跳出画面。\n镜头 4：@图片 6 的 UI 界面从画面右侧位移入画，像素武侠角色从画面右上角跳入，落在「三月廿七日」大字的右下方，张开双臂摆出热情展示的定格姿势，最终定格在该画面。\n整体像素武侠美术风格，色调统一浅蓝底，运镜连贯顺滑呈现一镜到底的连续位移与跟随，元素过渡自然、角色动作衔接流畅，画面无卡顿、无闪烁；文字与 UI 清晰稳定。","clips":[{"model":"seedance-2.5-flash","resolution":"720P","video":"https://img.kovapi.com/i/mp-2ee2d1750be8ebe3789d15e6.mp4","cost":"$1.80","verdict":"Flash: one take and the pixel style are right; one key frame unused."},{"model":"seedance-2.5","resolution":"720P","video":"https://img.kovapi.com/i/mp-d190ceb69b8b097b61b2e3b3.mp4","cost":"$2.37","verdict":"Seedance 2.5: all six key frames matched."}]}]}