Update README.md
Browse files
README.md
CHANGED
|
@@ -5,22 +5,23 @@ license_link: https://huggingface.co/mdmachine/flux.1-lite-8B-alpha-Hyper-8.Step
|
|
| 5 |
base_model:
|
| 6 |
- black-forest-labs/FLUX.1-dev
|
| 7 |
---
|
|
|
|
| 8 |
**FLUX Model Merge: Detail Enhancement and Acceleration**
|
| 9 |
=====================================================
|
| 10 |
|
| 11 |
-
This repository contains a merge of two FLUX models, with detail enhancement and acceleration techniques applied. The result consists of six files in total, divided into three quantized GGUF (Q8_0) and three optimized SAFETensors format (fp8_34m3fn_fast).
|
| 12 |
|
| 13 |
**Files:**
|
| 14 |
|
| 15 |
1. **GGUF Quantized Models (Q8_0)**:
|
| 16 |
-
- [
|
| 17 |
-
-
|
| 18 |
-
- [
|
| 19 |
|
| 20 |
2. **SAFETensors Format (fp8_34m3fn_fast)**:
|
| 21 |
-
- [Hyper-
|
| 22 |
-
- [Hyper-
|
| 23 |
-
- [
|
| 24 |
|
| 25 |
**Detail Enhancement Models Used:**
|
| 26 |
|
|
@@ -29,12 +30,12 @@ This repository contains a merge of two FLUX models, with detail enhancement and
|
|
| 29 |
|
| 30 |
**Optimization Credits:**
|
| 31 |
|
| 32 |
-
* ByteDance, a leading AI technology company, optimized the following models:
|
| 33 |
-
- Hyper-FLUX.1-dev-16steps
|
| 34 |
-
- Hyper-FLUX.1-dev-8steps
|
| 35 |
|
| 36 |
-
* Alimama Creative, a renowned NLP innovator, optimized the following model:
|
| 37 |
-
- FLUX.1-Turbo-Alpha
|
| 38 |
|
| 39 |
**Attribution and Licensing Notice:**
|
| 40 |
|
|
@@ -42,4 +43,4 @@ The FLUX.1 [dev] Model is licensed by Black Forest Labs, Inc. under the FLUX.1 [
|
|
| 42 |
|
| 43 |
Our model weights are released under the FLUX.1 [dev] [Non-Commercial License](https://huggingface.co/mdmachine/flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-fp8_e4m3fn_fast/blob/main/LICENSE.md).
|
| 44 |
|
| 45 |
-
This merge combines the strengths of these models, applying detail enhancement and acceleration techniques to create a unique and powerful AI model. We hope this contributes positively to the development of the NLP community!
|
|
|
|
| 5 |
base_model:
|
| 6 |
- black-forest-labs/FLUX.1-dev
|
| 7 |
---
|
| 8 |
+
|
| 9 |
**FLUX Model Merge: Detail Enhancement and Acceleration**
|
| 10 |
=====================================================
|
| 11 |
|
| 12 |
+
This repository contains a merge of two FLUX models, built upon the base model [Freepik's Flux.1-Lite-8B-alpha](https://huggingface.co/Freepik/flux.1-lite-8B-alpha), with detail enhancement and acceleration techniques applied. The result consists of six files in total, divided into three quantized GGUF (Q8_0) and three optimized SAFETensors format (fp8_34m3fn_fast).
|
| 13 |
|
| 14 |
**Files:**
|
| 15 |
|
| 16 |
1. **GGUF Quantized Models (Q8_0)**:
|
| 17 |
+
- [flux.1-lite-8B-alpha-Hyper-16.Steps-Detail.Plus.Steps.Q8_0_quantized](https://huggingface.co/mdmachine/)
|
| 18 |
+
- flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus.Steps.Q8_0_quantized](https://huggingface.co/mdmachine/)
|
| 19 |
+
- [flux.1-lite-8B-alpha-Turbo-8.Steps-Detail.Plus.Steps.Q8_0_quantized](https://huggingface.co/mdmachine/)
|
| 20 |
|
| 21 |
2. **SAFETensors Format (fp8_34m3fn_fast)**:
|
| 22 |
+
- [flux.1-lite-8B-alpha-Hyper-16.Steps-Detail.Plus-fp8_e4m3fn_fast](https://huggingface.co/mdmachine/flux.1-lite-8B-alpha-Hyper-16.Steps-Detail.Plus-fp8_e4m3fn_fast/tree/main)
|
| 23 |
+
- [flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus](https://huggingface.co/mdmachine/flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-fp8_e4m3fn_fast/tree/main)
|
| 24 |
+
- [flux.1-lite-8B-alpha-Turbo-8.Steps-Detail.Plus-fp8_e4m3fn_fast](https://huggingface.co/mdmachine/flux.1-lite-8B-alpha-Turbo-8.Steps-Detail.Plus-fp8_e4m3fn_fast/tree/main)
|
| 25 |
|
| 26 |
**Detail Enhancement Models Used:**
|
| 27 |
|
|
|
|
| 30 |
|
| 31 |
**Optimization Credits:**
|
| 32 |
|
| 33 |
+
* [ByteDance](https://huggingface.co/ByteDance), a leading AI technology company, optimized the following models:
|
| 34 |
+
- [Hyper-FLUX.1-dev-16steps](https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-FLUX.1-dev-16steps-lora.safetensors)
|
| 35 |
+
- [Hyper-FLUX.1-dev-8steps](https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-FLUX.1-dev-8steps-lora.safetensors)
|
| 36 |
|
| 37 |
+
* [Alimama Creative](https://huggingface.co/alimama-creative), a renowned NLP innovator, optimized the following model:
|
| 38 |
+
- [FLUX.1-Turbo-Alpha](https://huggingface.co/alimama-creative/FLUX.1-Turbo-Alpha)
|
| 39 |
|
| 40 |
**Attribution and Licensing Notice:**
|
| 41 |
|
|
|
|
| 43 |
|
| 44 |
Our model weights are released under the FLUX.1 [dev] [Non-Commercial License](https://huggingface.co/mdmachine/flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-fp8_e4m3fn_fast/blob/main/LICENSE.md).
|
| 45 |
|
| 46 |
+
This merge combines the strengths of these models, applying detail enhancement and acceleration techniques to create a unique and powerful AI model built upon [Freepik's Flux.1-Lite-8B-alpha](https://huggingface.co/Freepik/flux.1-lite-8B-alpha). We hope this contributes positively to the development of the NLP community!
|