Alternatives to Self Forcing Wan 2.1
200 apps like Self Forcing Wan 2.1, closest match first.
Top picks
- S
Sdnext
LaunchSD.Next is an open-source web interface for generating and editing images and video with a wide range of diffusion models. It runs on NVIDIA, AMD, Intel, Apple Silicon, or CPU setups. You can generate images or video from text or images, ed
Open source
- L
LTX 2.3
LaunchLTX 2.5 AI Video Generator is a web app for making short videos from text, a still image or audio. You describe a scene or upload a first frame, optionally add a last frame, pick a model and set the options, and the app generates a clip. Th
- M

Magi-1.AI
LaunchMAGI-1 is an open-source AI video generation model that creates video from a text prompt and an image. It is an autoregressive diffusion model that predicts video in chunks, so a clip can be extended one step at a time for a longer result,
Open source
- T
TokenFlow
LaunchOfficial Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)
Open source
- V
VibeFrame
LaunchVibeFrame lets a coding agent such as Claude Code, Codex or Cursor generate and assemble video. The agent gets commands to plan a video, generate assets with providers including Seedance, Grok, Runway, Kling and Gemini Omni, using your own
Open source
- C
CogVideoX-5B
LaunchThis Gradio demo integrates the CogVideoX-5B model, allowing you to perform video inference directly in your browser. It supports features like UpScale, RIFE, and other functionalities.
More like Self Forcing Wan 2.1
Autoregressive-Models-in-Vision-Survey
[TMLR 2025] A survey for the autoregressive models in vision

Luma Dream Machine
An AI model that makes high quality, realistic videos fast from text and images

guaardvark/guaardvark
Self-hosted AI studio exposing local image, video and music-video generation
Free Flux 3 AI – Image & Video Generator
Use Flux 3 AI, the multimodal AI image & video generator

SadHorse Studio
Create stunning 1080p AI video with SadHorse Studio, powered by the HappyHorse
Sora 2 - OpenAI's Revolutionary AI Video
AI Text-to-Video Creator — Cinematic, watermark-free
About Self Forcing Wan 2.1
Self Forcing Wan 2.1
Real-time video generation
Self Forcing trains autoregressive video diffusion models by simulating the inference process during training, performing autoregressive rollout with KV caching. It resolves the train-test distribution mismatch and enables real-time, streaming video generation on a single RTX 4090 while matching the quality of state-of-the-art diffusion models.
- Price
- Free
- Made by
- multimodalart
- Category
- AI
- Website
- huggingface.co/spaces/multimodalart/self-forcing









