Ir para o conteúdo

Seedance 2.0 Reference to Video

Integrar

ID do modelo bytedance/seedance-2.0/reference-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/bytedance/seedance-2.0/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Duration: 10s | Strict 16:9 Landscape | Native 4K UHD | 24fps. Genre: Cinematic Slice-of-Life Fantasy Comedy / Elemental Magic. Target: Ultra-realistic premium live-action fantasy cinema. Use @ image1 as the sole identity reference; preserve exactly as shown, ignoring only background, pose, framing, and text. Exactly one Character A, with no redesign, duplication, morphing, identity drift, outfit change, or hairstyle change. In an old witch’s kitchen, Character A attempts to make one cup of tea using elemental magic, but the spell becomes unexpectedly powerful. The scene begins with a table-level macro shot of a still ceramic cup of tea while Character A’s tired, unimpressed face remains softly blurred behind it. Character A reaches for the wand and raises it in profile. A thin orange-blue magical filament travels continuously from the wand tip through open space into the center of the tea, visibly making contact with the liquid and creating a subtle glowing ripple and warm reflection inside the cup; only after contact does the tea begin rotating. The stirring starts gently, then accelerates unnaturally fast, creating a small controlled whirlpool and a few droplets rising from the surface without splashing wildly. Character A watches with slightly widened eyes, then makes one quick reverse wand gesture to cancel the spell. The tea immediately becomes still. Character A lowers the wand onto the table, lifts the cup carefully, and takes one small sip. There is absolutely no disgust before tasting. After a brief beat, the excessive heat registers: Character A’s eyes narrow, brows pinch, nose wrinkles slightly, and the lips tighten into a restrained, exhausted grimace. Character A leans forward and spits the same mouthful of tea back into the same ceramic cup, keeping the lower face and cup visible together; show one small restrained spray of liquid leaving the mouth and landing back inside the cup, with no vomiting or excessive saliva. Character A then stares at the cup with quiet offended disbelief while lowering it toward the table, ending during the movement with no smile, camera look, victory pose, freeze frame, or fade. Camera language is cinematic macro depth with rack focus, tight profile, wand insert, readable over-the-shoulder magical contact, overhead tea-whirlpool detail, extreme eye close-up, and tight three-quarter reaction, maintaining consistent screen direction and avoiding chaotic camera shake or teleportation. Audio consists of quiet witch-kitchen ambience, wand ignition, a subtle magical hum, liquid swirling, cancellation sound, a small sip, restrained “ptuh,” soft liquid landing, and a disappointed exhale. Music is cozy, mischievous slice-of-life comedy using acoustic guitar, pizzicato strings, muted piano, playful clarinet, and brushed percussion, with no vocals; build gently during the magical stirring, briefly thin the score as the heat registers, then add one understated plucked accent when the tea lands back in the cup. Keep music below the sound effects and avoid boing sounds, circus music, meme sounds, or laugh tracks. Maintain strict causality: FILAMENT CONTACT → TEA STIRS → SPELL ESCALATES → SPELL CANCELLED → TEA STILL → SIP → HEAT REGISTERS → SAME MOUTHFUL SPAT BACK INTO SAME CUP → DEADPAN REGRET. Priority locks are identity, visible magical contact, continuous tea-state consistency, sip before reaction, the same mouthful visibly returning to the same cup, stable facial anatomy, restrained acting, realistic liquid physics, cinematic close-ups, and readable comedic timing. Negative prompt: duplicate character, duplicate cup, duplicate wand, duplicate tea, missing magical contact, magic hitting table or hand, reaction before sipping, new liquid appearing, whole cup spat out, vomiting, excessive saliva, broken mouth anatomy, premature stirring, instant violent whirlpool, large magical explosion, injury, identity drift, exaggerated acting, cartoon physics, anime, cheap CGI, plastic skin, discontinuity, frozen frames, subtitles, text, logo, watermark.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_c3dk4hgrd2tzlsymbg986itv/0-6Vz76mAQT0PWAMVCZaZAY_KTBfm8A8.png"
    ],
    "resolution": "480p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Esta solicitação: $ 0,705 705 créditos de API Executar nesta página

Obter chave de API
ByteDance Referência para vídeo Áudio nativoSaída em 4KEntradas de referência4–15 saté 4k #audio#references#consistency

Orienta um clipe de 4 a 15 segundos com som usando até 9 imagens, 3 vídeos e 3 clipes de áudio referenciados por nome.

Exemplos

Entrada
Saída · ~219 s

PromptDuration: 10s | Strict 16:9 Landscape | Native 4K UHD | 24fps. Genre: Cinematic Slice-of-Life Fantasy Comedy / Elemental Magic. Target: Ultra-realistic premium live-action fantasy cinema. Use @ image1 as the sole identity reference; preserve exactly as shown, ignoring only background, pose, framing, and text. Exactly one Character A, with no redesign, duplication, morphing, identity drift, outfit change, or hairstyle change. In an old witch’s kitchen, Character A attempts to make one cup of tea using elemental magic, but the spell becomes unexpectedly powerful. The scene begins with a table-level macro shot of a still ceramic cup of tea while Character A’s tired, unimpressed face remains softly blurred behind it. Character A reaches for the wand and raises it in profile. A thin orange-blue magical filament travels continuously from the wand tip through open space into the center of the tea, visibly making contact with the liquid and creating a subtle glowing ripple and warm reflection inside the cup; only after contact does the tea begin rotating. The stirring starts gently, then accelerates unnaturally fast, creating a small controlled whirlpool and a few droplets rising from the surface without splashing wildly. Character A watches with slightly widened eyes, then makes one quick reverse wand gesture to cancel the spell. The tea immediately becomes still. Character A lowers the wand onto the table, lifts the cup carefully, and takes one small sip. There is absolutely no disgust before tasting. After a brief beat, the excessive heat registers: Character A’s eyes narrow, brows pinch, nose wrinkles slightly, and the lips tighten into a restrained, exhausted grimace. Character A leans forward and spits the same mouthful of tea back into the same ceramic cup, keeping the lower face and cup visible together; show one small restrained spray of liquid leaving the mouth and landing back inside the cup, with no vomiting or excessive saliva. Character A then stares at the cup with quiet offended disbelief while lowering it toward the table, ending during the movement with no smile, camera look, victory pose, freeze frame, or fade. Camera language is cinematic macro depth with rack focus, tight profile, wand insert, readable over-the-shoulder magical contact, overhead tea-whirlpool detail, extreme eye close-up, and tight three-quarter reaction, maintaining consistent screen direction and avoiding chaotic camera shake or teleportation. Audio consists of quiet witch-kitchen ambience, wand ignition, a subtle magical hum, liquid swirling, cancellation sound, a small sip, restrained “ptuh,” soft liquid landing, and a disappointed exhale. Music is cozy, mischievous slice-of-life comedy using acoustic guitar, pizzicato strings, muted piano, playful clarinet, and brushed percussion, with no vocals; build gently during the magical stirring, briefly thin the score as the heat registers, then add one understated plucked accent when the tea lands back in the cup. Keep music below the sound effects and avoid boing sounds, circus music, meme sounds, or laugh tracks. Maintain strict causality: FILAMENT CONTACT → TEA STIRS → SPELL ESCALATES → SPELL CANCELLED → TEA STILL → SIP → HEAT REGISTERS → SAME MOUTHFUL SPAT BACK INTO SAME CUP → DEADPAN REGRET. Priority locks are identity, visible magical contact, continuous tea-state consistency, sip before reaction, the same mouthful visibly returning to the same cup, stable facial anatomy, restrained acting, realistic liquid physics, cinematic close-ups, and readable comedic timing. Negative prompt: duplicate character, duplicate cup, duplicate wand, duplicate tea, missing magical contact, magic hitting table or hand, reaction before sipping, new liquid appearing, whole cup spat out, vomiting, excessive saliva, broken mouth anatomy, premature stirring, instant violent whirlpool, large magical explosion, injury, identity drift, exaggerated acting, cartoon physics, anime, cheap CGI, plastic skin, discontinuity, frozen frames, subtitles, text, logo, watermark.

5 s480p16:9generate_audio: true$ 0,705 · 705 créditos de API

Prompt de @MahiraEhan no X

Criar uma solicitação

Os controles são gerados a partir do esquema do modelo. O código e o preço são atualizados conforme você os altera.

•obrigatório

Prompt de texto que orienta a geração de vídeo.

image_urls
Solte um arquivo ou · até 9

Referências de imagem para orientação do vídeo, limitadas a 9 imagens e sujeitas ao máximo de 12 arquivos em todas as modalidades. Cada imagem pode ter no máximo 30 MB e deve usar JPEG, PNG ou WebP. Use @Image1, @Image2 e os rótulos numerados subsequentes para identificar essas referências no prompt.

video_urls
Solte um arquivo ou · até 3

Referências de vídeo para geração, fornecidas como arquivos MP4 ou MOV e identificadas no prompt por @Video1, @Video2 e os rótulos numerados subsequentes. Cada uma deve ter resolução de aproximadamente 480p (640x640) a aproximadamente 720p (834x1112). O conjunto é limitado a 3 vídeos totalizando menos de 50 MB, com duração total de 2 a 15 segundos.

duration 5 s

Seleção da duração do vídeo: `auto` delega a escolha ao modelo usando o prompt, enquanto uma duração explícita deve ser de 4 a 15 segundos.

resolution

Resolução de saída: 480p prioriza a velocidade, 720p oferece equilíbrio, 1080p proporciona alta qualidade e 4k proporciona a maior qualidade.

aspect_ratio

Proporção da saída: 16:9 produz paisagem, 9:16 produz retrato/vertical, 1:1 produz quadrado e 21:9 produz ultrawide cinematográfico. Selecione `auto` para que o modelo escolha a proporção.

Avançado audios · bitrate_mode · codec
audio_urls
Solte um arquivo ou · até 3

As referências de áudio para orientação do vídeo exigem pelo menos uma referência de imagem ou vídeo acompanhando. Forneça arquivos MP3 ou WAV de no máximo 15 MB cada, com no máximo 3 arquivos e duração total limitada a 15 segundos. Identifique-os no prompt usando @Audio1, @Audio2 e os rótulos numerados subsequentes.

bitrate_mode padrão standard

Escolha a taxa de bits da codificação de saída: 'standard' mantém o padrão, enquanto 'high' solicita que o modelo melhore a qualidade da codificação em troca de um arquivo maior.

codec padrão auto

Seleção do codec de vídeo: `auto` mantém o comportamento padrão do codec, `H264` seleciona H.264 e `H265` seleciona H.265.

POST /run/bytedance/seedance-2.0/reference-to-video?wait=20 cotação → $ 0,705
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/bytedance/seedance-2.0/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Duration: 10s | Strict 16:9 Landscape | Native 4K UHD | 24fps. Genre: Cinematic Slice-of-Life Fantasy Comedy / Elemental Magic. Target: Ultra-realistic premium live-action fantasy cinema. Use @ image1 as the sole identity reference; preserve exactly as shown, ignoring only background, pose, framing, and text. Exactly one Character A, with no redesign, duplication, morphing, identity drift, outfit change, or hairstyle change. In an old witch’s kitchen, Character A attempts to make one cup of tea using elemental magic, but the spell becomes unexpectedly powerful. The scene begins with a table-level macro shot of a still ceramic cup of tea while Character A’s tired, unimpressed face remains softly blurred behind it. Character A reaches for the wand and raises it in profile. A thin orange-blue magical filament travels continuously from the wand tip through open space into the center of the tea, visibly making contact with the liquid and creating a subtle glowing ripple and warm reflection inside the cup; only after contact does the tea begin rotating. The stirring starts gently, then accelerates unnaturally fast, creating a small controlled whirlpool and a few droplets rising from the surface without splashing wildly. Character A watches with slightly widened eyes, then makes one quick reverse wand gesture to cancel the spell. The tea immediately becomes still. Character A lowers the wand onto the table, lifts the cup carefully, and takes one small sip. There is absolutely no disgust before tasting. After a brief beat, the excessive heat registers: Character A’s eyes narrow, brows pinch, nose wrinkles slightly, and the lips tighten into a restrained, exhausted grimace. Character A leans forward and spits the same mouthful of tea back into the same ceramic cup, keeping the lower face and cup visible together; show one small restrained spray of liquid leaving the mouth and landing back inside the cup, with no vomiting or excessive saliva. Character A then stares at the cup with quiet offended disbelief while lowering it toward the table, ending during the movement with no smile, camera look, victory pose, freeze frame, or fade. Camera language is cinematic macro depth with rack focus, tight profile, wand insert, readable over-the-shoulder magical contact, overhead tea-whirlpool detail, extreme eye close-up, and tight three-quarter reaction, maintaining consistent screen direction and avoiding chaotic camera shake or teleportation. Audio consists of quiet witch-kitchen ambience, wand ignition, a subtle magical hum, liquid swirling, cancellation sound, a small sip, restrained “ptuh,” soft liquid landing, and a disappointed exhale. Music is cozy, mischievous slice-of-life comedy using acoustic guitar, pizzicato strings, muted piano, playful clarinet, and brushed percussion, with no vocals; build gently during the magical stirring, briefly thin the score as the heat registers, then add one understated plucked accent when the tea lands back in the cup. Keep music below the sound effects and avoid boing sounds, circus music, meme sounds, or laugh tracks. Maintain strict causality: FILAMENT CONTACT → TEA STIRS → SPELL ESCALATES → SPELL CANCELLED → TEA STILL → SIP → HEAT REGISTERS → SAME MOUTHFUL SPAT BACK INTO SAME CUP → DEADPAN REGRET. Priority locks are identity, visible magical contact, continuous tea-state consistency, sip before reaction, the same mouthful visibly returning to the same cup, stable facial anatomy, restrained acting, realistic liquid physics, cinematic close-ups, and readable comedic timing. Negative prompt: duplicate character, duplicate cup, duplicate wand, duplicate tea, missing magical contact, magic hitting table or hand, reaction before sipping, new liquid appearing, whole cup spat out, vomiting, excessive saliva, broken mouth anatomy, premature stirring, instant violent whirlpool, large magical explosion, injury, identity drift, exaggerated acting, cartoon physics, anime, cheap CGI, plastic skin, discontinuity, frozen frames, subtitles, text, logo, watermark.",
    "images": [
      "https://content.doitong.com/dev-api/2026/10/21/req_c3dk4hgrd2tzlsymbg986itv/0-6Vz76mAQT0PWAMVCZaZAY_KTBfm8A8.png"
    ],
    "resolution": "480p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Executar esta solicitação

Sua chave permanece neste navegador: ela é enviada somente à Doitong API e salva (localStorage) apenas se você marcar Lembrar. Obter uma chave de API

Sobre Seedance 2.0 Reference to Video

Modelo de vídeo com múltiplas referências da ByteDance: envie personagens, produtos, locais, uma referência de movimento ou câmera e um clipe de voz ou música, depois invoque-os no prompt como @Image1, @Video1, @Audio1 e assim por diante. Mantém as identidades consistentes entre cortes e gera áudio sincronizado. É necessária pelo menos uma referência de imagem ou vídeo, e todas as referências juntas podem ter no máximo 12 arquivos. Saída de 480p a 4K.

Parâmetros

Envie o nome canônico ou o nome nativo, não ambos. Nomes canônicos

NomeTipo PadrãoPermitido Descrição
promptobrigatório
Tipostring
Prompt de texto que orienta a geração de vídeo.
image_urlsopcional images
Tipourl[] · image
≤ 9 itens
Referências de imagem para orientação do vídeo, limitadas a 9 imagens e sujeitas ao máximo de 12 arquivos em todas as modalidades. Cada imagem pode ter no máximo 30 MB e deve usar JPEG, PNG ou WebP. Use @Image1, @Image2 e os rótulos numerados subsequentes para identificar essas referências no prompt.
video_urlsopcional videos
Tipourl[] · video
≤ 3 itens
Referências de vídeo para geração, fornecidas como arquivos MP4 ou MOV e identificadas no prompt por @Video1, @Video2 e os rótulos numerados subsequentes. Cada uma deve ter resolução de aproximadamente 480p (640x640) a aproximadamente 720p (834x1112). O conjunto é limitado a 3 vídeos totalizando menos de 50 MB, com duração total de 2 a 15 segundos.
audio_urlsopcional audios
Tipourl[] · audio
≤ 3 itens
As referências de áudio para orientação do vídeo exigem pelo menos uma referência de imagem ou vídeo acompanhando. Forneça arquivos MP3 ou WAV de no máximo 15 MB cada, com no máximo 3 arquivos e duração total limitada a 15 segundos. Identifique-os no prompt usando @Audio1, @Audio2 e os rótulos numerados subsequentes.
resolutionopcional
Tipoenum
Padrão720p
480p720p1080p4k
Resolução de saída: 480p prioriza a velocidade, 720p oferece equilíbrio, 1080p proporciona alta qualidade e 4k proporciona a maior qualidade.
durationopcional
Tipoenum
Padrãoauto
auto456789101112131415
Seleção da duração do vídeo: `auto` delega a escolha ao modelo usando o prompt, enquanto uma duração explícita deve ser de 4 a 15 segundos.
aspect_ratioopcional
Tipoenum
Padrãoauto
auto21:916:94:31:13:49:16
Proporção da saída: 16:9 produz paisagem, 9:16 produz retrato/vertical, 1:1 produz quadrado e 21:9 produz ultrawide cinematográfico. Selecione `auto` para que o modelo escolha a proporção.
generate_audioopcional
Tipoboolean
Padrãotrue
Ative para acompanhar o vídeo com áudio sincronizado. O áudio gerado inclui fala sincronizada com os movimentos dos lábios, ambiente e efeitos sonoros.
bitrate_modeopcional
Tipoenum
Padrãostandard
standardhigh
Escolha a taxa de bits da codificação de saída: 'standard' mantém o padrão, enquanto 'high' solicita que o modelo melhore a qualidade da codificação em troca de um arquivo maior.
codecopcional
Tipoenum
Padrãoauto
autoH264H265
Seleção do codec de vídeo: `auto` mantém o comportamento padrão do codec, `H264` seleciona H.264 e `H265` seleciona H.265.
obrigatório Nome canônico, também aceito

Os parâmetros de arquivo aceitam uma URL https:// pública, um URI data: de até 10 MB ou o file_url de um upload. Arquivos

Saída

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "bytedance/seedance-2.0/reference-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 705,
    "usd": "0.705",
    "charged": 705,
    "refunded": 0
  },
  "input": {
    "prompt": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone",
    "images": [
      "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png"
    ],
    "resolution": "720p",
    "duration": 5
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "seed": 42
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Seus arquivos, sua escolhaCada outputs[].url é uma cópia em nosso armazenamento: mantida para sempre (cobrada por GB-mês) ou por 7 dias gratuitamente, conforme a configuração da sua conta ou ?storage=.
Mesmo formato em todos os modelostype, url, content_type, width, height e duration, para imagens, vídeos e áudios. output é o próprio objeto de resultado do modelo.
Campos da saída
video
object {url, content_type, file_name, file_size}Arquivo de vídeo produzido pela geração.
seed
integerValor de seed aplicado durante a geração.

Mais modelos: Referência para vídeo

Para agentes de IA: esta página em Markdown está em https://doitong.com/pt-BR/developers/models/bytedance/seedance-2.0/reference-to-video.md. Todos os modelos e guias: https://doitong.com/developers/llms.txt