ComfyUI Node: Wan Chunked I2V Sampler ♾️

Authored by gregtee2

Created

Updated

2 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

VideoChunkTools

Inputs

model WANVIDEOMODEL
vae WANVAE
start_image IMAGE
total_frames INT
chunk_frames INT
width INT
height INT
keep_proportion
  • stretch
  • crop
  • pad
crop_position
  • center
  • top
  • bottom
  • left
  • right
steps INT
cfg FLOAT
shift FLOAT
seed INT
force_offload BOOLEAN
scheduler
  • euler
  • euler/beta
  • unipc
  • unipc/beta
  • dpm++
  • dpm++/beta
  • dpm++_sde
  • dpm++_sde/beta
  • deis
  • lcm
  • lcm/beta
  • longcat_distill_euler
  • flowmatch_distill
  • flowmatch_causvid
  • res_multistep
enable_vae_tiling BOOLEAN
model_b WANVIDEOMODEL
split_step INT
cfg_b FLOAT
text_embeds WANVIDEOTEXTEMBEDS
text_embed_sequence TEXT_EMBED_SEQUENCE
clip_embeds WANVIDIMAGE_CLIPEMBEDS
feta_args FETAARGS
context_options WANVIDCONTEXT
noise_aug_strength FLOAT
start_latent_strength FLOAT
end_latent_strength FLOAT
riflex_freq_index INT
tile_x INT
tile_y INT
tile_stride_x INT
tile_stride_y INT
end_image IMAGE
end_blend_chunks INT

Outputs

IMAGE

INT

INT

Extension: ComfyUI_VideoChunkTools

ComfyUI nodes for generating long videos by splitting into overlapping chunks with rolling reference frames.

Authored by gregtee2

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more