Upload 4 files

README.md

@@ -2,12 +2,12 @@
 
 ## Quantized FLUX Transformer with Hyper-SD LoRA
 
-This repository contains a pre-trained model file `flux-fp8-hyper8-transformers-lora.pt`, a quantized FLUX transformer model merged with Hyper-SD LoRA weights, optimized for efficient inference.
+This repository contains quantized FLUX transformer model merged with Hyper-SD a,d Alimama LoRA weights, optimized for efficient inference.
 
 ### Model Details
 
 - **Base Model**: FLUX.1-dev transformer from Black Forest Labs
-- **LoRA**: Hyper-SD from ByteDance
+- **LoRA**: Hyper-SD from ByteDance and Alimama
 - **Quantization**: FP8 (e5m2 format)
 - **LoRA Scale**: 0.125
 

flux-fp8-transformers-hyper8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95434e438535ffb789097b7ae70d7a52d0d64fa897e9fa44e4e564da9d53feb4
+size 11910940464

flux-fp8-transformers-turbo-alpha-fused.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5924423127d2b47da991e75c291abc7f69e3c01d467c58f676df25930ce809f
+size 12264690472

flux-fp8-transformers.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95434e438535ffb789097b7ae70d7a52d0d64fa897e9fa44e4e564da9d53feb4
+size 11910940464