AEmotionStudio/flashvsr-models

Model

FlashVSR Model Mirror (AEmotionStudio)

0

8 commits

3 linked in READMEs

updated Mar 23, 2026

See the code

README

FlashVSR Model Mirror (AEmotionStudio)

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

Model Files

FileDescriptionSize
FlashVSR1_1.safetensorsDiT v1.1 weights (one-step diffusion backbone)~5.7 GB
Wan2.1_VAE.safetensorsWAV2.1 VAE decoder~254 MB
LQ_proj_in.safetensorsLow-quality 4× projection encoder~576 MB
TCDecoder.safetensorsTiny Conditional Decoder (for Tiny/Tiny-Long modes)~181 MB
Prompt.safetensorsCross-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

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.

AEmotionStudio/flashvsr-models

Model

FlashVSR Model Mirror (AEmotionStudio)

0

8 commits

3 linked in READMEs

updated Mar 23, 2026

See the code

README

FlashVSR Model Mirror (AEmotionStudio)

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

Model Files

FileDescriptionSize
FlashVSR1_1.safetensorsDiT v1.1 weights (one-step diffusion backbone)~5.7 GB
Wan2.1_VAE.safetensorsWAV2.1 VAE decoder~254 MB
LQ_proj_in.safetensorsLow-quality 4× projection encoder~576 MB
TCDecoder.safetensorsTiny Conditional Decoder (for Tiny/Tiny-Long modes)~181 MB
Prompt.safetensorsCross-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

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.