Load VAE

KSampler

ConditioningZeroOut

FluxGuidance

ModelSamplingSD3

HunyuanImageToVideo

Text Encode Hunyuan Video (ImageToVideo)

CLIP Vision Encode

Load CLIP Vision

Load Image

VAE Decode (Tiled)

Video Combine 🎥🅥🅗🅢

Unet Loader (GGUF)

DualCLIPLoader (GGUF)

Anything Everywhere3

Load Models

IMAGE

MASK

positive

start_image

latent

clip_vision

image

CLIP_VISION_OUTPUT

CLIP_VISION

MODEL

CLIP

model

negative

latent_image

LATENT

samples

conditioning

CONDITIONING

clip

clip_vision_output

images

audio

meta_batch

Filenames

makisekurisu

<h4 style="text-align: start;">v1 “concat”</h4><p> <a href="https://huggingface.co/city96/HunyuanVideo-I2V-gguf/tree/original" target="_blank">https://huggingface.co/city96/HunyuanVideo-I2V-gguf/tree/original</a></p><p><br></p><h4 style="text-align: start;">v2 “replace”</h4><p> <a href="https://huggingface.co/city96/HunyuanVideo-I2V-gguf/tree/main" target="_blank">https://huggingface.co/city96/HunyuanVideo-I2V-gguf/tree/main</a> </p>

hunyuan image to video

OpenArt

Workflows

Active Sessions

hunyuan image to video

Description

v1 “concat”

v2 “replace”

Discussion

Loading...