Add MixedPrecisionOps compatible fp8mixed qwen_image_edit_2509 with sensitive layers kept in high precision and using full_precision_matrix_mult (#11)
Browse files- Add MixedPrecisionOps compatible fp8mixed qwen_image_edit_2509 with sensitive layers kept in high precision and using full_precision_matrix_mult (2c425ab26567be2f69c1eaca985a13d7a0e68e4e)
Co-authored-by: Silver <[email protected]>
split_files/diffusion_models/qwen_image_edit_2509_fp8mixed.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c742e8c584c11f65d846816b334d2c25a89e0a196d2790a813c6bf943e40a492
|
| 3 |
+
size 20533579421
|