Nodes/ComfyUI-FL-MiniMaxH3/FL MiniMax H3 Prompt Timeline
ComfyUI Node

FL MiniMax H3 Prompt Timeline

Creates MiniMax H3 video/audio latents with both strict latent-time prompt scheduling and a fast semantic timeline conditioning.

By filliptm·Created 19 days ago·Updated about 24 hours ago· 0
FL MiniMax H3 Prompt Timeline
  • clip
  • vae
  • audio_vae
  • prompt_schedule
  • prompt_envelopes
  • ref_images
  • ref_videos
  • ref_video_audios
  • ref_audios
  • scheduled
  • latent
  • semantic
  • timeline
global_prompt
width1344
height768
length124
time_unitseconds
bpm120.0
transition_modecosine
transition_frames4
affect_audiovideo only
duration_policystrict
ref_image_sizematch
timeline
CategoryFL/MiniMax H3/Prompting

Inputs (21)

NameTypeDefaultDescription
clipCLIPMiniMax H3 text encoder used for the global and scheduled prompts.
vaeVAEMiniMax H3 video VAE used for reference images and reference videos.
audio_vaeVAEMiniMax H3 audio VAE used for audio references and video soundtracks.
global_promptSTRINGPersistent subject, style, and scene context. This is the default conditioning under scheduled masks and is prepended to every scheduled prompt.
widthINT134432–16384Width of the native H3 video latent in output pixels.
heightINT76832–16384Height of the native H3 video latent in output pixels.
lengthINT1245–3600Requested frame count at H3's fixed 24 fps. H3 snaps it to the 17k+5 frame grid.
time_unitCOMBOsecondsLegacy unit used only by manual timeline headers. Connected prompt schedules own their time unit; H3 video always runs at 24 fps.
bpmFLOAT120.01–999Legacy constant BPM used only for manual timelines in beats mode. Connected prompt schedules carry exact detected timing.
transition_modeCOMBOcosineTransition curve between contiguous sections in the manual timeline.
transition_framesINT40–96Manual timeline transition width in 24 fps video frames.
affect_audioCOMBOvideo onlyChoose whether scheduled text masks affect only H3 video tokens or both generated video and audio tokens.
duration_policyCOMBOstrictstrict rejects ranges past the H3 duration; clamp trims them; fit scales the full schedule to the aligned H3 duration.
ref_image_sizeCOMBOmatchmatch limits reference image area to the output canvas; max uses H3's maximum reference short edge.
timelineoptSTRINGLegacy manual ordered time ranges followed by prompt text. Used only when prompt_schedule is not connected.
prompt_scheduleoptFL_PROMPT_SCHEDULEOptional exact-time schedule, such as the output of FL Audio Beat Prompt Schedule. When connected, it overrides the manual timeline.
prompt_envelopesoptCOMFY_AUTOGROW_V3Optional audio-reactive prompt envelopes. Each unique prompt adds one conditioning evaluation per sampling step.
ref_imagesoptCOMFY_AUTOGROW_V3Optional H3 reference images. Add sockets as needed.
ref_videosoptCOMFY_AUTOGROW_V3Optional H3 reference videos. Add sockets as needed.
ref_video_audiosoptCOMFY_AUTOGROW_V3Optional soundtracks paired by index with reference videos.
ref_audiosoptCOMFY_AUTOGROW_V3Optional standalone H3 audio references. Add sockets as needed.

Outputs (4)

NameTypeDescription
scheduledCONDITIONINGStrict latent-time conditioning for the first H3 sampling pass.
latentLATENTNative nested MiniMax H3 video/audio latent.
semanticCONDITIONINGSingle semantic timeline conditioning for faster low-denoise refinement passes.
timelineFL_H3_TIMELINEReusable encoded H3 timeline for applying the same schedule after spatial resizing.