
Upload an image, use that image to deduce the clue, and you can generate a 16-second video. At 512 resolution, it took me 6 minutes and cost around 70 coins.
TEXT to 16-second Video
1494 Views5 Likes54 Favorites
Aquila
NaN.NaN.NaN Update
Follow
Aquila
2025-03-03 Update
Follow
Workflow introduction
Upload an image, use that image to deduce the clue, and you can generate a 16-second video. At 512 resolution, it took me 6 minutes and cost around 70 coins.
Nodes Information
16
LoadImage
Bjornulf_ShowText
GetImageSizeAndCount
LoadWanVideoT5TextEncoder
Note
RH_Captioner
VHS_VideoCombine
WanVideoContextOptions
WanVideoDecode
WanVideoEmptyEmbeds
WanVideoModelLoader
WanVideoSampler
WanVideoTextEncode
WanVideoTorchCompileSettings
WanVideoVAELoader
easy cleanGpuUsed
Upload an image, use that image to deduce the clue, and you can generate a 16-second video. At 512 resolution, it took me 6 minutes and cost around 70 coins.
Nodes Information
16
LoadImage
Bjornulf_ShowText
GetImageSizeAndCount
LoadWanVideoT5TextEncoder
Note
RH_Captioner
VHS_VideoCombine
WanVideoContextOptions
WanVideoDecode
WanVideoEmptyEmbeds
WanVideoModelLoader
WanVideoSampler
WanVideoTextEncode
WanVideoTorchCompileSettings
WanVideoVAELoader
easy cleanGpuUsed
