Home Seedream 5 Pricing Start creating
Dreamina Seedance 2.0

Seedance 2.0 uzvedņu rokasgrāmata

Profesionāla līmeņa video ģenerēšana ar iebūvētu audio, dziļu multimodālo atsauci un nevainojamu rediģēšanu — apkopota 18 anotētos uzvedņu piemēros.

18
Uzvedņu piemēri
5
Rokasgrāmatas sadaļas
Native
Audio + video

Par šo rokasgrāmatu

Dreamina Seedance 2.0 ir profesionāla līmeņa video ģenerēšanas modelis, kas sākotnēji atbalsta apvienotu audio un video izvadi ar izcilu semantisko izpratni un multimodālo mijiedarbību. Šī rokasgrāmata iepazīstina ar galvenajām metodēm — teksta formulām, atsauces kontroli, teksta renderēšanu, attēlu/video atsaucēm un nedestruktīvu rediģēšanu — ar 18 oficiāliem piemēriem.

Visi tālāk redzamie video un attēli ir autonomi ģenerēti ar Seedance/Seedream vizuālajiem modeļiem. Pārpublicēts ar BytePlus ModelArk atļauju.
01

Vispārīgie principi

1.1 Teksta instrukciju pamatformula

Seedance 2.0 izceļas ar dabiskās valodas loģikas ievērošanu. Elastīgi kombinējiet šos elementus, lai tie atbilstu jūsu radošajam mērķim:

  • Subjekts + darbība — loģiskais pamats. Skaidri definējiet, kas veic kādu darbību.
  • Atmosfēra — iestatiet kopējo toni, aprakstot telpisko fonu, apgaismojuma detaļas vai specifisku vizuālo stilu.
  • Skaņas dizains — uzlabotas instrukcijas var ietvert ainas vai apkārtējās vides skaņas efektus imersīvai, sinhronizētai audiovizuālajai izvadei.
1.2 Atsauces kontrole multimodālajām ievadēm

Papildus teksta aprakstiem fiksējiet ideālo kadra stāvokli ar atsauces materiāliem. Seedance 2.0 atbalsta padziļinātu attēlu, audio un video atsauču izmantošanu.

  • Savā uzvednē skaidri norādiet atsauces objektu — piemēram, “Izmantot Image 1 kompozīciju” vai “Atbilst Video 2 kustībai”.
  • Modelis iegūst galvenās iezīmes no atsauces un apvieno tās ar jūsu tekstu, saglabājot augstu precizitāti un paredzamību, vienlaikus pieļaujot radošas variācijas.
02

Teksta renderēšana

Seedance 2.0 ģenerē salasāmu tekstu T2V (Text-to-Video), I2V (Image-to-Video), R2V (Reference-to-Video) un V2V (Video-to-Video) režīmos. Tas automātiski pielāgo fonta stilu un krāsu jūsu ainai un sniedz detalizētu kontroli pār stilu, laiku un izkārtojumu.

2.1 Slogani

Seedance 2.0 automātiski nosaka ainas kontekstu, lai piemeklētu atbilstošāko fonta estētiku. Stingrai zīmola konsekvencei izmantojiet kopā ar logo atsauci (skatīt 3.2).

Prompt template
[Text Content] + [Timing] + [Positioning] + [Entrance/Appearance Style], [Visual Attributes (Color, Font Style)]
2.2 Subtitri
Prompt template
Display subtitles at the bottom-center with the text. The subtitles must be perfectly synchronized with the audio rhythm and pacing.
2.3 Runas burbuļi
Prompt template
[Character] says, "[Dialogue]." Speech bubbles appear around the character containing the spoken text.
Labākā prakse
  • Parasta leksika. Standarta, plaši atpazīstami vārdi tiek renderēti visprecīzāk.
  • Izvairieties no mazpazīstamiem vārdiem. Sarežģīti vai reti termini var radīt nekonsekventas rakstzīmes.
  • Samaziniet speciālo simbolu skaitu. Sarežģītas vai nestandarta pieturzīmes pasliktina fonta precizitāti.
2.1 · Example 1
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
Hand-drawn comic style: Three people are sitting around a table enjoying the fried chicken shown in Image 1, with a friendly and joyful atmosphere. The frame then gradually blurs, and the text "Bite", "Laugh", "Seedance" in order appears in the center of the screen.
2.2 · Example 2 Aizkadra balss
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
I2V: A time-lapse of a mountain landscape transitioning from a vast, starry night to a vibrant dawn. Voiceover: A deep, serene male voice says: 'In the vast silence of the cosmos, our world is but a fleeting moment. Yet, within it, life defiantly thrives.' > Text Integration: Render the narration as subtitles at the bottom-center. Subtitles must be perfectly synchronized with audio timing.
2.2 · Example 3 Dublēšana
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
R2V: A shot of these two people in Image 1 chatting in a modern office. The woman speaks first with a playful tone: "You always arrive right on time, don't you just love that perfect timing?" followed by the man's smiling reply: "I have my own rhythm." > Text Integration: Render the dialogue as subtitles at the bottom-center of the screen. Subtitles should appear sequentially as each character speaks.
2.3 · Example 4 Rotaļu laukuma skats
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
The two characters from Image 1, both dressed in sportswear, are running on the school playground. The girl looks at the boy, smiling confidently as she says: "We can definitely do it!". Cut to a close-up of the boy. He hesitates and replies: "Are you sure?". Cut back to a medium close-up of the girl. She speaks in a light, upbeat tone: "Yes!" Her demeanor is bright and resolute. Speech bubbles containing the corresponding lines appear around the speaking character.
2.3 · Example 5 Ābeļdārzs
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
Refer to the character design of the girl in Image 1 and Image 2. The scene is set in an apple field: the girl picks one apple, takes a bite, smiles and says "This is the real deal!". A speech bubble pops up beside the girl, with this line written inside.
03

Attēla atsauce

Seedance 2.0 atbalsta vairāku perspektīvu atsauces subjektiem un vairāku attēlu atsauces ainu izkārtojumiem un secībām. Ja jūsu darba plūsmai nepieciešama noteikta secība, augšupielādējiet attēlus secīgi un norādiet tos uzvednē kā Image 1, Image 2, … Image N.

3.1 Subjekta atsauce no vairākām perspektīvām
Prompt template
Refer to / Extract / Combine / Use the [Subject] from [Image N] to generate [Scene Description], maintaining consistent [Subject] features.
3.2 Vairāku attēlu atsauce
Prompt template
Refer to / Extract / Combine / Follow the [Description of referenced elements] from [Image N] to generate [Scene Description], while maintaining the consistency of [Referenced Elements].
3.1 · Example 1 Sadzīves elektronika
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
Use the cameras featured in Image 1, Image 2 and Image 3. Replace the original background with a white one, and place the cameras on a white table. The shooting lens first focuses on the cameras in close-up, then slowly rotates 360° with the cameras as the main subject, clearly displaying the front, sides and back of each camera.
3.1 · Example 2 Mājas un dzīvesveids
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
In a warm-toned home setting, present the thermos shown in the reference image in a medium shot. Then smoothly push the camera into a close-up of the thermos. Next, a hand naturally enters the frame off-screen, gently grips the thermos body and picks it up. The camera follows the slight rotating motion of the hand to showcase the thermos.
3.1 · Example 3 Tēli
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
Refer to the image of the woman in Image 1, Image 2 and Image 3, and generate a scene of her eating a cake in a coffee shop.
3.2 · Example 4 Logo atsauce
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
The scene is set on an aerial corridor in a neon-drenched futuristic metropolis, where flying vehicles and holographic ads intertwine. Featuring the girl from Reference Image 2, the sequence opens with a medium shot of her releasing a silver floating lantern embedded with a holographic projection. The camera then pulls back to reveal floating lanterns flooding the sky, which gradually converge at the center of the frame to form the logo from Reference Image 1. The entire piece adopts a 3D cyberpunk sci-fi animation style.
3.2 · Example 5 Vairāku subjektu atsauce
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
Using the cat and dog from the reference Image 1 and Image 2 as prototypes, the scene unfolds in a cozy apartment. The dog is lying on the ground eating dog food when the cat approaches, extending a paw to nudge the dog. The dog pauses its meal upon noticing the cat, and the cat snuggles up next to the dog. The entire scene features a warm colored tone.
3.2 · Example 6 Vairāku elementu atsauce
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
The scene is set in the restaurant from Image 4 with people coming and going. The girl from Image 1, wearing the clothes from Image 2, is organizing the items on the counter. The boy, a customer, from Image 3 approaches her to ask for her contact information. The logo from Image 5 remains in the bottom right corner throughout.
3.2 · Example 7 Vairāku paneļu secības atsauce
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
Refer to the sequence in Image 1 to create an intense high-energy fight sequence. All frame compositions from Image 1 shall be presented in strict predefined order, after which the two characters engage in fierce, fast-paced combat.
3.2 · Example 8 Secības atsauce
Izvade
Atsauces attēls
Reference image 1 Image 1
Uzvedne
Refer to the composition in Image 3. A girl (her character design refers to Image 1) is waiting for her father to finish cooking, and she says: "아빠, 배고파요! 밥 다 됐어요?" Then the camera pans right and cuts to the frame and composition shown in Image 4. The father (his character design refers to Image 2) replies to her: "거의 다 됐어, 조금만 기다려!" Next, the camera cuts back to a close-up shot of the daughter's slightly disappointed facial expression, and she says: "아직 멀었어요? 맛있는 냄새 나는데..." Then the shot switches to a close-up of the father's face, and he says: "이제 진짜 금방이야. '빨리빨리' 하지 말고 손부터 씻고 와!"
04

Video atsauce

Seedance 2.0 atbalsta video bāzētas atsauces kustībai, kameras kustībai un vizuālajiem efektiem. Augšupielādējiet video secīgi un norādiet tos kā Video 1, Video 2, … Video N.

4.1 Kustības atsauce
Prompt template
Refer to the [Motion Description] from [Video N] to generate [Scene Description], keeping the motion details consistent.
4.2 Kameras kustības atsauce
Prompt template
Refer to the [Camera Movement Description] from [Video N] to generate [Scene Description], keeping the scene consistent.
4.3 Vizuālo efektu (VFX) atsauce
Prompt template
Refer to the [VFX Effects Description] from [Video N] to generate [Scene Description], keeping the special effects consistent.
4.1 · Example 1 Māksliniecisks
Izvade
References
Reference image 1 Image 1
Video 1
Uzvedne
Refer to the character movements and shot language in Video 1 to create a fight scene with the character from Image 2 on the left and the character from Image 1 on the right. Include intense background music.
4.1 · Example 2 Mārketings
Izvade
Atsauces video
Video 1
Uzvedne
Referencing the running shape of the horse in the video, generate a scene: a golden steed runs on the grassland, then freezes its magnificent running posture and turns into a horse-shaped gold pendant.
4.2 · Example 3
Izvade
References
Reference image 1 Image 1
Video 1
Uzvedne
Referring to the camera movement in Video 1, create a concept video for a science and technology park, with the tall building in Image 1 as the visual center, also using a first-person diving perspective, to reflect the sense of technology in the park from Image 1.
4.3 · Example 4 Video producēšana
Izvade
References
Reference image 1 Image 1
Video 1
Uzvedne
Refer to the golden particle effects in Video 1, so that when the character in Image 1 plays the flute, the same particle effects surround their body.
4.3 · Example 5 Radošie efekti
Izvade
References
Reference image 1 Image 1
Video 1
Uzvedne
Refer to the special effects shown in Video 1 to generate identical wings for the girl in Image 1, ensuring the wing formation trajectory follows the exact same motion path and sequence depicted in the video.
05

Video rediģēšana

Seedance 2.0 atbalsta nedestruktīvu video rediģēšanu — elementu pievienošanu, noņemšanu vai modificēšanu; pagarināšanu uz priekšu vai atpakaļ; un celiņu pabeigšanu vairākos klipos. Oriģinālie segmenti tiek saglabāti nevainojamai nepārtrauktībai.

5.1 Elementu pievienošana, noņemšana vai modificēšana
Prompt template
Adding: At [Timestamp] and [Spatial Location] of [Video N], add [intended element].
Removing: Remove [Element] from [Video N], keeping the rest unchanged.
Modifying: Replace [original element] in [Video N] with [intended element].
5.2 Video pagarināšana
Prompt template
Extend [Video N] forward/backward + [Description of extended content]
Generate content before/after [Video N] + [Description of extended content]
5.3 Celiņu pabeigšana
Prompt template
[Video 1] + [Transition Description] + followed by [Video 2] + [Transition Description] + followed by [Video 3]
Note: Celiņu pabeigšana atbalsta līdz 3 video klipiem ar kopējo ilgumu 15 sekundes. Modelis automātiski apgriež savienojošos segmentus nemanāmai sintēzei.
5.1 · Example 1 Pievienot elementus
Izvade
Atsauces video
Video 1
Uzvedne
Add snacks such as fried chicken and pizza to the countertop in Video 1.
5.1 · Example 2 Noņemt elementus
Izvade
Atsauces video
Video 1
Uzvedne
Remove everything that isn't office stuff from the table in Video 1, keeping the rest of the video content unchanged.
5.1 · Example 3 Modificēt elementus
Izvade
References
Reference image 1 Image 1
Video 1
Uzvedne
Replace the perfume featured in Video 1 with the face cream from Image 1, with all original motions and camera work preserved.
5.2 · Example 4 Pagarināt uz priekšu
Izvade
Atsauces video
Video 1
Uzvedne
Generate the content after Video 1: the two men who are late run towards them, the five people finally meet and have a friendly chat.
5.2 · Example 5 Pagarināt atpakaļ
Izvade
Atsauces video
Video 1
Uzvedne
Extend the opening segment of Video 1: Set up an over-the-shoulder shot of the man in a hoodie, and the man says: "It's not that bad. You're just stressed. Everyone goes through this, you just need to keep going."
5.3 · Example 6
Izvade
Atsauces video
Video 1
Video 2
Uzvedne
Video 1. The moment a leaf falls to the ground, it sets off a special effect of golden particles. A gust of wind blows by, leading into Video 2.

Vai esat gatavs radīt ar Seedance 2.0?

Sāciet ģenerēt video ar apvienotu audio, atsauces kontroli un nedestruktīvu rediģēšanu — tieši Doitong.

Sākt radīt