Nodes/HunyuanVideo-1.5 nodes/HunyuanVideo CFG
ComfyUI Node

HunyuanVideo CFG

To use CFG with HunyuanVideo

By yuanyuan-spec·Created 9 months ago·Updated 8 months ago· 27
HunyuanVideo CFG
  • transformer_config
  • sr_transformer_config
  • reference_image
  • hyvid_cfg
  • hyvid_sr_cfg
promptA close-up shot captures a scene on a polished, light-colored granite kitchen counter, illuminated by soft natural light from an unseen window. Initially, the frame focuses on a tall, clear glass filled with golden, translucent apple juice standing next to a single, shiny red apple with a green leaf still attached to its stem. The camera moves horizontally to the right. As the shot progresses, a white ceramic plate smoothly enters the frame, revealing a fresh arrangement of about seven or eight more apples, a mix of vibrant reds and greens, piled neatly upon it. A shallow depth of field keeps the focus sharply on the fruit and glass, while the kitchen backsplash in the background remains softly blurred. The scene is in a realistic style.
negative_promptAerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion
prompt_rewritefalse
flow_shift
guidance_scale6.00
num_videos_per_prompt1
video_length121
seed0
task_typei2v
CategoryHunyuanVideoWrapper1.5

Inputs (12)

NameTypeDefaultDescription
promptSTRINGA close-up shot captures a scene on a polished, light-colored granite kitchen counter, illuminated by soft natural light from an unseen window. Initially, the frame focuses on a tall, clear glass filled with golden, translucent apple juice standing next to a single, shiny red apple with a green leaf still attached to its stem. The camera moves horizontally to the right. As the shot progresses, a white ceramic plate smoothly enters the frame, revealing a fresh arrangement of about seven or eight more apples, a mix of vibrant reds and greens, piled neatly upon it. A shallow depth of field keeps the focus sharply on the fruit and glass, while the kitchen backsplash in the background remains softly blurred. The scene is in a realistic style.
negative_promptSTRINGAerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortionNegative prompt(s) that describe what should NOT be shown in the generated video.
prompt_rewriteBOOLEANfalseWhether to rewrite the prompt.
flow_shiftFLOATWhen the resolution is 480p, the recommended shift value is 5, and when the resolution is 720p, the recommended shift value is 7. If you do not set this value, it will be automatically configured according to the recommendations of this rule.
guidance_scaleoptFLOAT6.00Scale to encourage the model to better follow the prompt. `guidance_scale > 1` enables classifier-free guidance.
num_videos_per_promptoptINT11–100Number of videos to generate per prompt.
video_lengthoptINT1211–200Number of frames to generate.
seedoptINT00–2147483647
transformer_configoptHYVID15TRANSFORMERCONFIG
task_typeoptCOMBOi2v2 options: t2v, i2v
sr_transformer_configoptHYVID15TRANSFORMERCONFIG
reference_imageoptIMAGEReference image.

Outputs (2)

NameTypeDescription
hyvid_cfgHYVID15CFG
hyvid_sr_cfgHYVID15CFG