Ir para o conteúdo
PipeListadosHospedado

Wan 2.2 text to video

Generate one silent video from a text description with Wan 2.2. No uploaded image or video is required. For a first run, edit the positive prompt to describe your subject, movement, camera, lighting and setting, then keep the 640 × 640 size, 5-second duration and 16 FPS defaults. The negative prompt independently discourages unwanted content and visual traits; its supplied Chinese text includes artifacts, static frames and clutter.

Workflow details

FamíliaWanResolução1024x1024Estimado VRAMNot yet characterizedPublicadorSweet Tea AutomationAtualizado25 de out.Bnota

Perfil de execução

Publicador
Sweet Tea Automation
Status
Listados
Versão
Checking published version…
Atualizado
25 de out. de 2026

Hover nodes for Pipe controls

Core

Primary Pipe surface

Positive prompt

CLIPTextEncode

Negative prompt

CLIPTextEncode

Output size

EmptyHunyuanLatentVideo

Duration

PrimitiveFloat

Frame rate

PrimitiveFloat

Lightning mode

PrimitiveBoolean

Extended

Additional surfaced controls

Initial sampling

KSamplerAdvanced

Standard sampling steps

PrimitiveInt

Standard guidance

PrimitiveFloat

Standard stage handoff

PrimitiveInt

Lightning sampling steps

PrimitiveInt

Lightning guidance

PrimitiveFloat

Lightning stage handoff

PrimitiveInt

Initial Lightning strength

LoraLoaderModelOnly

Finishing Lightning strength

LoraLoaderModelOnly

Finishing sampling

KSamplerAdvanced

Video encoding

SweetTeaPreviewVideo

Output

Initial noise schedule

ModelSamplingSD3

Finishing noise schedule

ModelSamplingSD3

Video bit depth

CreateVideo

What you need

Hardware and download-size estimates are not available yet.

Output

  • Generated video · video

Requisitos

Modelos

6

Pacotes de nós

1

Fontes

1 fonte
Sweet TeaFonte