AEmotionStudio/flashvsr-models

FlashVSR Model Mirror (AEmotionStudio)

Mirror of FlashVSR v1.1 model weights for ComfyUI-FFMPEGA.

Model Files

File	Description	Size
FlashVSR1_1.safetensors	DiT v1.1 weights (one-step diffusion backbone)	~5.7 GB
Wan2.1_VAE.safetensors	WAV2.1 VAE decoder	~254 MB
LQ_proj_in.safetensors	Low-quality 4× projection encoder	~576 MB
TCDecoder.safetensors	Tiny Conditional Decoder (for Tiny/Tiny-Long modes)	~181 MB
Prompt.safetensors	Cross-attention conditioning embeddings	~4 MB

Variants

• FlashVSR Full — Best quality, full VAE decode (~12-16 GB VRAM)
• FlashVSR Tiny — Fast mode with TCDecoder (~8-12 GB VRAM)
• FlashVSR Tiny Long — Streaming for long videos, lowest VRAM (~8-12 GB)

All variants share the same weight files. The variant determines which pipeline and decoder components are used at inference time.

Usage

These models are automatically downloaded by ComfyUI-FFMPEGA when selecting any flashvsr_* model from the upscale_model dropdown.

Manual installation:

ComfyUI/models/FlashVSR/
├── FlashVSR1_1.safetensors
├── Wan2.1_VAE.safetensors
├── LQ_proj_in.safetensors
├── TCDecoder.safetensors
└── Prompt.safetensors

Attribution

• Original model: FlashVSR (CVPR 2026) by Junhao Zhuang et al.
• Original weights: JunhaoZhuang/FlashVSR
• ComfyUI adaptation (BSA-free): 1038lab/ComfyUI-FlashVSR
• ComfyUI integration weights: 1038lab/FlashVSR

License

GPL-3.0 — See LICENSE for full text.

The FlashVSR model weights are released under the GNU General Public License v3.0. All usage must comply with the original license terms from the FlashVSR authors.