AEmotionStudio/ai-upscale-models

Model

AI Upscale Models for FFMPEGA

2

4 commits

5 linked in READMEs

updated Mar 9, 2026

See the code

README

AI Upscale Models for FFMPEGA

Pre-trained super-resolution models for use with ComfyUI-FFMPEGA's AI Upscale feature.

Models are automatically downloaded on first use — no manual setup required.

Models

FileArchitectureScaleSizeVRAMBest For
RealESRGAN_x4plus.pthRRDBNet (GAN)4×67 MB~2 GBGeneral real-world photos
RealESRGAN_x4plus_anime_6B.pthRRDBNet (compact)4×18 MB~1 GBAnime, cartoon, illustration
Real_HAT_GAN_SRx4.pthHAT (hybrid attention)4×170 MB~4 GBSOTA quality, fine detail
003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pthSwinIR-Large4×48 MB~3 GBClean images, classical SR

All models output 4× resolution. For 2× output, the upscaler runs at 4× then applies high-quality Lanczos downscaling.

Usage in FFMPEGA

  1. Set llm_model → none
  2. Set no_llm_mode → ai_upscale
  3. Choose upscale_model (e.g. hat_x4 for best quality)
  4. Choose upscale_scale (4 or 2)
  5. Connect an image or video input and run

Model Loading

Models are loaded via spandrel, which auto-detects the architecture from the checkpoint file. No additional dependencies are needed beyond what ComfyUI already provides.

Credits

comfyui
ffmpega
image-super-resolution
image-to-image
real-esrgan
spandrel
super-resolution
swinir
upscaling
video-processing

AEmotionStudio/ai-upscale-models

Model

AI Upscale Models for FFMPEGA

2

4 commits

5 linked in READMEs

updated Mar 9, 2026

See the code

README

AI Upscale Models for FFMPEGA

Pre-trained super-resolution models for use with ComfyUI-FFMPEGA's AI Upscale feature.

Models are automatically downloaded on first use — no manual setup required.

Models

FileArchitectureScaleSizeVRAMBest For
RealESRGAN_x4plus.pthRRDBNet (GAN)4×67 MB~2 GBGeneral real-world photos
RealESRGAN_x4plus_anime_6B.pthRRDBNet (compact)4×18 MB~1 GBAnime, cartoon, illustration
Real_HAT_GAN_SRx4.pthHAT (hybrid attention)4×170 MB~4 GBSOTA quality, fine detail
003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pthSwinIR-Large4×48 MB~3 GBClean images, classical SR

All models output 4× resolution. For 2× output, the upscaler runs at 4× then applies high-quality Lanczos downscaling.

Usage in FFMPEGA

  1. Set llm_model → none
  2. Set no_llm_mode → ai_upscale
  3. Choose upscale_model (e.g. hat_x4 for best quality)
  4. Choose upscale_scale (4 or 2)
  5. Connect an image or video input and run

Model Loading

Models are loaded via spandrel, which auto-detects the architecture from the checkpoint file. No additional dependencies are needed beyond what ComfyUI already provides.

Credits

comfyui
ffmpega
image-super-resolution
image-to-image
real-esrgan
spandrel
super-resolution
swinir
upscaling
video-processing