Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →artokun/video-extend
Extend / continue a video temporally with Pusa 2.2 in ComfyUI — temporal flowmatching (the flowmatch_pusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into the continuation. Covers the kijai wanvideo_2_2_14B_Pusa_extension graph, model/LoRA slots + downloads, noise/length/scheduler settings, chaining multiple extensions, VRAM tiers, go
Passed 18 of 20 test cases with the skill, and 5 of 20 without it.
and 21 more in the full report
15 fixed6 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
What parameter value should be passed into noisy_steps on WanVideoAddPusaNoise for the HIGH sampler pass versus the LOW sampler pass in the standard distilled Pusa extension graph?
| Checked | Without skill | With skill |
|---|---|---|
| Sets noisy_steps to 0 for the HIGH sampler pass. | Missed | Passed |
| Sets noisy_steps to 2 for the LOW sampler pass. | Missed | Passed |
The instructions your model reads when the skill loads.
Pusa extends a video temporally. It continues and lengthens an existing clip
rather than regenerating it from scratch. It does this on the
ComfyUI-WanVideoWrapper stack (kijai) using the WAN 2.2 T2V A14B dual
HIGH/LOW models you already have for wan-t2v-video, plus the small Pusa V1
LoRAs and a Pusa-specific sampling path: the flowmatch_pusa scheduler and
the WanVideoAddPusaNoise node. The input clip is encoded with
WanVideoEncode and injected as the first latents of the generation, which
is what carries the existing motion and content into the continuation.
The official reference graph is kijai's
wanvideo_2_2_14B_Pusa_extension_example_01.json (in
ComfyUI-WanVideoWrapper/example_workflows/). This skill is built directly from
that workflow plus the live node schemas.
Relationship to
wan-t2v-video: Pusa rides on the exact same WanVideoWrapper stack. Same T2V A14B HIGH/LOW fp8 models, same UMT5 text encoder, same WAN VAE, same block-swap/torch-compile machinery. The only new downloads are the two Pusa V1 LoRAs (~1.9 GB total). Readwan-t2v-videofirst for the base stack; this skill is the temporal-extension delta on top of it.
Verification note: every node, model, LoRA filename and setting below was confirmed against the live ComfyUI
/object_info(WanVideoWrapper installed) and against kijai's example workflow JSON + HF repo (June 2026). Where a value is a starting recommendation rather than a hard requirement it's flagged. Don't substitute a node you can't confirm withinstall_custom_node(action: "list") /create_workflow (action:"node_info").
WAN is a flow-matching video model: sampling integrates a velocity field from noise to a clean latent, and every frame normally shares the same denoising timestep. Pusa's contribution (Vectorized Timestep Adaptation) is to make the timestep per-frame. The frames you already have can be held at (or near) t = 0 (clean) while the new frames start from t = 1 (noise), and the model
test cases passed, vs 5 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.