Wan 2.2
Open-weight video diffusion from Alibaba.
Open Source 12–48 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Workstation GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
ComfyUI-AnimateDiff-Evolved
Animation motion modules for ComfyUI.
Open Source 10–16 GB VRAMRuns locally
Actually FreeNo SignupOpen SourceWatermark-FreeHobbyist-FriendlyPlugin
Requires: ComfyUI
Visit ComfyUI-AnimateDiff-EvolvedUpdated 2026-03-28 · Direct link
Hardware requirements
Runs locally · High-end GPU (16–24 GB)
Min VRAM
10 GB
Rec. VRAM
16 GB
Min RAM
16 GB
Rec. RAM
32 GB
Disk
20 GB
GPU class
High-end GPU
Via ComfyUIApple Silicon ✓GPU RequiredQuant: FP16
SD1.5 motion runs on 10 GB. SDXL motion wants 16–24 GB.
Screenshot placeholder · ComfyUI-AnimateDiff-Evolved
What is ComfyUI-AnimateDiff-Evolved?
Maintained AnimateDiff implementation for ComfyUI. Adds motion modules to SD1.5 / SDXL workflows to turn image pipelines into short animations, with motion LoRAs and context options for longer clips.
Pros & cons
Pros
- Most flexible AnimateDiff impl
- Context window keeps long clips coherent
- Pairs with ControlNet
Cons
- VRAM-heavy for SDXL motion
- AnimateDiff style now superseded by Wan/Hunyuan for many uses
What's actually free?
Free / OSS.
✓ Actually FreeNo SignupOpen SourceWatermark-Free
Alternatives
HunyuanVideo
13B open-weight cinematic text-to-video.
Open Source 24–48 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Workstation GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
CogVideoX 5B
Open-source text-to-video diffusion from THUDM.
Open Source 12–24 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free