Updated license to Apache 2.0

Update Readme.md - added last video

Added Q8 GGUF models from cmeka / SeedVR2-GGUF

Rename seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors_test to seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors

Test

Added Q4 GGUF models from cmeka / SeedVR2-GGUF

Added Q4 GGUF models from cmeka / SeedVR2-GGUF

Added Q4 GGUF models from cmeka / SeedVR2-GGUF

Added GGUF models & remove test

Rename seedvr2_ema_7b_sharp_fp8_e4m3fn.safetensors to seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors

Rename seedvr2_ema_7b_fp8_e4m3fn.safetensors to seedvr2_ema_7b_fp8_e4m3fn_mixed_block35_fp16.safetensors

FP8 conversion of seedvr2_ema_7b_sharp.pth with last block kept in FP16 to avoid line/tile artifacts (no metadata)

FP8 conversion of seedvr2_ema_7b.pth with last block kept in FP16 to avoid line/tile artifacts (no metadata)

seedvr2_ema_7b_sharp_fp8_e4m3fn - FP8 conversion of seedvr2_ema_7b_sharp.pth with last block kept in FP16 to avoid line/tile artifacts

Update README.md

seedvr2_ema_7b_fp8_e4m3fn - FP8 conversion of seedvr2_ema_7b.pth with last block kept in FP16 to avoid line/tile artifacts

initial commit