SkyReels-V2: Infinite-Length Film Generative Model by Skywork

SkyReels-V2 is the first open-source infinite-length film generative model using Diffusion Forcing. Built on Wan2.1, it supports T2V, I2V, and autoregressive video generation.

S

SkyReels-V2

VideoText-to-VideoImage-to-VideoDiffusion ForcingInfinite-LengthOpen Source

SkyReels-V2 is an infinite-length film generative model by Kunlun Tech (Skywork), employing an AutoRegressive Diffusion-Forcing architecture for SOTA open-source video generation. Built on Wan2.1, it supports Text-to-Video (T2V), Image-to-Video (I2V), and infinite-length Diffusion Forcing (DF) generation via both synchronous and asynchronous inference modes. Available in 14B and 1.3B parameter sizes at 540P and 720P resolutions. LoRA adapters are also available for fine-tuning. ComfyUI support via Kijai's WanVideoWrapper.

DeveloperKunlun Tech (Skywork AI)
Release Date2025-04-21
ArchitectureAutoRegressive Diffusion-Forcing Transformer
Base ModelWan2.1 (Wan-AI)
LicenseSkyReels-V2 Community License
Model Sizes14B (full) / 1.3B (lightweight)
CapabilitiesText-to-Video (14B), Image-to-Video (14B), Diffusion Forcing (14B/1.3B) : infinite-length autoregressive
Output Resolutions540P (960×544) / 720P (1280×720)
Max Frames97~1457 frames (4s–60s+ at 24fps)
VRAM (540P)~51.2 GB (14B) / ~14.7 GB (1.3B)

Overview

SkyReels-V2 is the first open-source video generative model employing an AutoRegressive Diffusion-Forcing architecture, achieving SOTA performance among publicly available models. It synergizes Multi-modal Large Language Models (MLLM), Multi-stage Pretraining, Reinforcement Learning, and the Diffusion Forcing Framework to enable infinite-length film generation.

Model Variants

Three model types are available, each with multiple resolutions and precision options:

TypeDescriptionAvailable SizesPrecision
Diffusion Forcing (DF)Infinite-length autoregressive video generation; supports both T2V and I2V tasks in synchronous or asynchronous modes14B (540P/720P), 1.3B (540P)fp16, fp8_e4m3fn, fp8_e5m2
Text-to-Video (T2V)Standard text-to-video generation14B (540P/720P)fp16, fp8_e4m3fn, fp8_e5m2
Image-to-Video (I2V)Image-conditioned video generation14B (540P/720P)fp16, fp8_e4m3fn, fp8_e5m2
SkyReels A2Controllable video generation for assembling arbitrary visual elements; Apache-2.014B (fp8)fp8_e4m3fn

Key Features

  • Infinite-Length Generation: Uses Diffusion Forcing with autoregressive frame prediction to generate arbitrarily long videos beyond single-clip limits
  • Synchronous & Asynchronous Inference: Synchronous for faster generation, asynchronous for better instruction following and visual consistency
  • Video Extension: Extend existing videos with the DF model by passing a video path
  • Start/End Frame Control: Control both first and last frames of generated videos
  • Prompt Enhancement: Built-in prompt enhancer using Qwen2.5-32B-Instruct
  • TeaCache Acceleration: Optional caching for faster inference
  • Offload Support: CPU offloading reduces peak VRAM requirements

ComfyUI Setup

These models are packaged by Kijai for use with the WanVideoWrapper custom node. Place diffusion models in ComfyUI/models/diffusion_models/ and LoRAs in ComfyUI/models/loras/.