Nodes/Comfyui-zhenzhen/Concurrent Submit | zhenzhen-seedance2.5-standard-low-price
ComfyUI Node

Concurrent Submit | zhenzhen-seedance2.5-standard-low-price

Seedance 2.5 video on the cheap site, with a 30-reference multimodal floor

By T8mars·Created about a year ago·Updated 3 days ago· 749
Concurrent Submit | zhenzhen-seedance2.5-standard-low-price
  • api_config
  • image1
  • image2
  • image3
  • image4
  • image5
  • image6
  • image7
  • image8
  • image9
  • image10
  • image11
  • image12
  • image13
  • image14
  • image15
  • image16
  • image17
  • image18
  • image19
  • image20
  • image21
  • image22
  • image23
  • image24
  • image25
  • image26
  • image27
  • image28
  • image29
  • image30
  • video1
  • video2
  • video3
  • video4
  • video5
  • video6
  • video7
  • video8
  • video9
  • video10
  • audio1
  • audio2
  • audio3
  • audio4
  • audio5
  • audio6
  • audio7
  • audio8
  • audio9
  • audio10
  • task
◄modelseedance-2.5-standard-t2v►
◄prompt►
◄seconds4►
◄resolution480p►
◄ratioadaptive►
◄generate_audiotrue►
◄return_last_framefalse►
◄seed-1►
◄skip_errorfalse►

ByteDance's Seedance 2.5 video model on the domestic discount site, and the most input-hungry node in this pack: thirty image slots, ten video slots, ten audio slots. That's not decoration - Seedance's whole selling point is multimodal reference, and the multi model variants will actually use a pile of reference frames plus reference clips plus reference audio in one generation. If you've ever wanted to say "make a video that looks like these shots, moves like this clip, and has this sound," this is the wrapper.

It's a video node, so it runs in the shared video pool (10 workers) and returns a COMFLY_VIDEO_FUTURE task. Collect with Concurrent Collect Videos (ComflyConcurrent_Video_Await), which waits on up to 10 tasks and gives you video_1…video_10 in order. And like the other low-price nodes, it takes an api_config from the Comfly Seedance2 Low Price Settings node rather than a bare apikey field.

The inputs

  • model - six variants: seedance-2.5-standard-t2v / -i2v / -multi, plus the same three with -global-. The multi variants unlock the reference orgy; the global ones route internationally.
  • prompt - the direction, multiline.
  • seconds - -1 (auto) or 4–15.
  • resolution - 480p, 720p, 1080p, 2k, 4k, or native1080p (the pack's favorite: native 1080p output that the changelog calls "效果炸裂").
  • ratio - adaptive, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9.
  • image1…image30, video1…video10, audio1…audio10 - the reference buffet.
  • generate_audio - on by default (Seedance generates synchronized audio); flip off to save money on silent tests.
  • return_last_frame - off by default; enable to get the final frame as a usable still.
  • seed - -1 (random) to 2147483647.

Install

cd ComfyUI/custom_nodes
git clone https://github.com/T8mars/Comfyui-zhenzhen

Or ComfyUI Manager → search Comfyui-zhenzhen → restart, then build api_config with the settings node and your domestic token (api.seedance.nz).

Gotchas

  • Reference counts are multiplicative, and so is the bill. The README notes that reference video seconds are counted in the price - a 5s reference clip adds to what a 5s output costs. Keep refs short.
  • 4k and native1080p are the expensive lanes. "Low price" is the site's discount, not a promise of cheap 4K; the resolution/seconds choice is where the real budget lives.
  • The video pool is shared with every video node in the pack. Ten concurrent jobs across all of them - a busy batch will queue. Tune COMFLY_VIDEO_CONCURRENCY if you own the box and want more.
Categoryzhenzhen/Seedance2 Low Price/Concurrent Submit

Inputs (60)

NameTypeDefaultDescription
modelCOMBOseedance-2.5-standard-t2v6 options: seedance-2.5-standard-t2v, seedance-2.5-standard-i2v, seedance-2.5-standard-multi, seedance-2.5-global-standard-t2v, seedance-2.5-global-standard-i2v, seedance-2.5-global-standard-multi
promptSTRING—
secondsCOMBO428 options: -1, 4, 5, 6, 7, 8, +22
resolutionCOMBO480p6 options: 480p, 720p, 1080p, 2k, 4k, native1080p
ratioCOMBOadaptive7 options: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16, +1
api_configoptZHENZHEN_SEEDANCE2_CONFIG—
image1optIMAGE—
image2optIMAGE—
image3optIMAGE—
image4optIMAGE—
image5optIMAGE—
image6optIMAGE—
image7optIMAGE—
image8optIMAGE—
image9optIMAGE—
image10optIMAGE—
image11optIMAGE—
image12optIMAGE—
image13optIMAGE—
image14optIMAGE—
image15optIMAGE—
image16optIMAGE—
image17optIMAGE—
image18optIMAGE—
image19optIMAGE—
image20optIMAGE—
image21optIMAGE—
image22optIMAGE—
image23optIMAGE—
image24optIMAGE—
image25optIMAGE—
image26optIMAGE—
image27optIMAGE—
image28optIMAGE—
image29optIMAGE—
image30optIMAGE—
video1optVIDEO—
video2optVIDEO—
video3optVIDEO—
video4optVIDEO—
video5optVIDEO—
video6optVIDEO—
video7optVIDEO—
video8optVIDEO—
video9optVIDEO—
video10optVIDEO—
audio1optAUDIO—
audio2optAUDIO—
audio3optAUDIO—
audio4optAUDIO—
audio5optAUDIO—
audio6optAUDIO—
audio7optAUDIO—
audio8optAUDIO—
audio9optAUDIO—
audio10optAUDIO—
generate_audiooptBOOLEANtrue—
return_last_frameoptBOOLEANfalse—
seedoptINT-1-1–2147483647—
skip_erroroptBOOLEANfalse—

Outputs (1)

NameTypeDescription
taskCOMFLY_VIDEO_FUTURE—