Wan 2.1 image-to-video with optional end frame
Generate a silent video from a starting image and a text prompt using Wan 2.1 Fun InP 1.3B, optionally guiding the ending with a second image.
Loading this version’s controls and setup…
Workflow details
Workflow details
Perfil de execução
- Publicador
- Sweet Tea Automation
- Status
- Listados
- Versão
- v0.1.5
- Atualizado
- 4 de nov. de 2026
Hover nodes for Pipe controls
Core
Primary Pipe surface
Start image
LoadImage
Positive prompt
CLIPTextEncode
Video shape
WanFunInpaintToVideo
Video playback
CreateVideo
End frame
LoadImage
Extended
Additional surfaced controls
Negative prompt
CLIPTextEncode
Sampling
KSampler
Image conditioning
CLIPVisionEncode
Skip-layer guidance
SkipLayerGuidanceDiT
Noise schedule
ModelSamplingSD3
Attention tuning
UNetTemporalAttentionMultiply
What you need
- Model files
- 7.7 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Output
- Generated video · video
Requisitos
Modelos
4- Encontrado
Clip Vision · 1.18 GB · SAFETENSORS · FP16 + I64 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
umt5_xxl_fp8_e4m3fn_scaled.safetensors
EncontradoText encoder · 6.27 GB · SAFETENSORS · U8 + FP16 + FP32 + FP8 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
- Encontrado
VAE · 242 MB · SAFETENSORS · BF16 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
wan2.1_fun_inp_1.3B_bf16.safetensors
Não resolvidoDiffusion model · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Pacotes de nós
2- Encontrado
Pacote de nós · Unknown
- Encontrado
Pacote de nós · GitHub · tea-time-labs/sweet-tea-nodes
Fontes
1 fonte
Fontes
1 fonteArtefatos de modelo
1 artefato
Artefatos de modelo
1 artefato7331e5ba-902a-4cdc-9251-bad3e5cd247c-comfy-wan2-1-fun-inp-draft-0.1.5.tea
tea · 29,1 KB · SHA-256 f7cdb42d6b24…51c1
Download file