SkyReels V1: The first and most advanced open-source human-centric video foundation model

Temporal LoRA gating for LTX 2.3 workflows in ComfyUI.

🎬 Director-grade Seedance 2.0 prompt OS for OpenClaw + Hermes agents — 28 skills, T2V/I2V/V2V/FLF2V, multi-clip sequences, zh/ja/ko support, IP-safe rewrites & pro delivery. Powered by MyClaw.ai

Generative image model runtimes for MLX.

OpenMM-Arena

A frame2frame, video2video Video Editor based on the stable-diffusion

Wan 2.2 WebUI (I2V + S2V).

[ECCV 2026] TriMotion: Modality-Agnostic Camera Control for Video Generation

Contains the notebooks and workflows configured to run inference from Wan 2.2 Animate with ComfyUI on Kaggle T4 GPUs smoothly

WAN 2.x inference with ComfyUI

A project just for collecting all the best open source projects in order to found them quickliy.

Free, high-efficiency Python CLI tool & batch video generator for ByteDance's new SeeDance 2.5 (Doubao Video) model. Features multi-threading, Text-to-Video, and Image-to-Video workflows via Volcano Ark (火山引擎), Fal.ai, and Replicate APIs. Supports automatic batch outputs.

Claude Code / Codex CLI skill — 2,366 real Seedance 2.0 video-generation prompts. Structural scaffolds, corpus search, source attribution. Zero dependencies.

即梦 Seedance 2.0 inside ComfyUI — I2V & T2V nodes for AI short drama production

FlexiClip: Locality-Preserving Free-Form Character Animation

ComfyUI custom node to filter and trim image batches based on face similarity and eye openness for I2V chaining.

swiftified video generation

Anime image-to-video on Wan2.2 A14B + AnimeGen + Lightning — a clean CLI with aspect-correct sizing and motion presets.

generate image or video by image and text, you can free generate it (only for test)

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors