WorldFoundry
English中文

FastVideo CausalWan2.2

FastVideo CausalWan2.2

NVIDIA / FastVideo eight-step causal Wan2.2 image-to-video: 832×480 area budget, 81 requested frames, guidance 1, 16 fps.

Edit this pageGitHubMarkdown

FastVideo CausalWan2.2 is an eight-step causal Wan2.2 rollout: video comes out in three-latent-frame blocks while the stack routes between high- and low-noise experts. WorldFoundry keeps expert KV / cross-attention caches independent and applies self-forcing re-noise on a fixed shifted flow schedule. Native roles cover both Wan2.2 experts, T5, VAE, and cache traversal. Pipeline: FastVideoCausalWanPipeline. Alias fastvideo-causal-wan resolves here. Related HF id: FastVideo/CausalWan2.2-I2V-A14B-Preview-Diffusers.

Official paper teaser: Closed-loop simulation workflow. A policy model (here, Alpamayo 1 ( NVIDIA, 2026a ) ) or user sends an action to the AlpaSim simulation runtime. AlpaSim updates the simulation state and forwards the context to.
Official paper teaser: Closed-loop simulation workflow. A policy model (here, Alpamayo 1 ( NVIDIA, 2026a ) ) or user sends an action to the AlpaSim simulation runtime. AlpaSim updates the simulation state and forwards the context to.

Paper: arXiv 2606.03159. Project: nvidia.github.io/flashdreams. Code: NVIDIA/FlashDreams. Preview weights: FastVideo/CausalWan2.2-I2V-A14B-Preview-Diffusers (Apache-2.0). CPU contract tests and checkpoint-backed GPU inference pass.

Build your run

Pipeline
FastVideoCausalWanPipelineworldfoundry.pipelines.fastvideo_causal_wan.pipeline_fastvideo_causal_wan
TaskInteractive Video interactive-video
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
Runnerworldfoundry.pipeline
Loadingfrom_pretrained
Invocationnative_or_standard_invocation
worldfoundry-eval run \
  fastvideo-causal-wan2.2-i2v-14b \
  --pipeline.task-profile interactive-video \
  --json

What it is for

Causal Wan2.2 fast video. Not the full Wan2.2 family card.

Launch worldfoundry-eval run fastvideo-causal-wan2.2-i2v-14b and an input image.

Runtime contract

Required: prompt and image; artifacts: fastvideo-causal-wan2.2-i2v-14b.mp4.

KnobDefault
Size832×480 area budget; 16-pixel-aligned canvas follows the source aspect ratio (1280×704 → 848×464)
Frames81 from WorldFoundry; FastVideo's current official runner emits 73 for the same 81-frame request
Steps8
Guidance1
FPS16
Block3 latent frames

Run in WorldFoundry

Status: checkpoint-backed 81-frame inference verified at 848×464 on an H100. Run worldfoundry-eval run fastvideo-causal-wan2.2-i2v-14b with an image. The matching official FastVideo request produced 73 frames because its denoiser drops the final two latent frames. The shared frames have matching composition and forward motion; pixel-level parity remains open because the implementations use different random generators and latent precision. License: Apache-2.0. Catalog VRAM is unset.