mdmachine commited on
Commit
009763c
·
verified ·
1 Parent(s): db28bf2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -8
README.md CHANGED
@@ -18,9 +18,7 @@ This repository contains merged models, built upon the base models:
18
  - [Freepik's Flux.1-Lite-8B-alpha](https://huggingface.co/Freepik/flux.1-lite-8B-alpha)
19
  - [Flux-dev-de-distill](https://huggingface.co/nyanko7/flux-dev-de-distill)
20
 
21
- Detail enhancement and acceleration techniques have been applied, particularly optimized for NVIDIA 4XXX cards (maybe 3XXX too). The goal is to have high efficiency accelerated models with lower overhead.
22
-
23
- The (de-re-destill | Distilled) models can be used with CFG remaining at 1-ish. Also the baked-in accelerators work (mostly) as intended. This is a result of workflow optimization by-products. Things can be added/removed or changed at any time.
24
 
25
  **====================================**
26
 
@@ -51,7 +49,12 @@ The (de-re-destill | Distilled) models can be used with CFG remaining at 1-ish.
51
  - **Best of Flux: Style Enhancing LoRA** (Weight: 0.06) ([Model Link](https://civitai.com/models/821668))
52
 
53
  **Distillation Used:**
54
- - **Flux distilled lora** (Weight: Hyper - .65 | Turbo - 0.50) ([Model Link](https://civitai.com/models/977247/flux-distilled-lora))
 
 
 
 
 
55
 
56
  3. **GGUF Quantized Models (Q8_0)**:
57
  - [flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-Distilled-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/Lite-8B-Plus/Distilled/GGUF/Q8_0/flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-Distilled-V2-Q8_0.gguf)
@@ -71,22 +74,22 @@ The (de-re-destill | Distilled) models can be used with CFG remaining at 1-ish.
71
  **Re-Distillation Used:**
72
  - **Flux distilled lora** (Weight: -1.00) ([Model Link](https://civitai.com/models/977247/flux-distilled-lora))
73
 
74
- 1. **SAFETensors Format V2 (fp8_34m3fn_fast)**:
75
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/FP8/Version%202/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2.safetensors)
76
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/FP8/Version%202/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2.safetensors)
77
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/FP8/Version%202/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2.safetensors)
78
 
79
- 4. **GGUF Quantized Models (Q8_0)**:
80
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q8_0/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0.gguf)
81
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q8_0/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0.gguf)
82
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q8_0/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0.gguf)
83
 
84
- 5. **GGUF Quantized Models (Q6_K)**:
85
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q6_K/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K.gguf)
86
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q6_K/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K.gguf)
87
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q6_K/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K.gguf)
88
 
89
- 6. **GGUF Quantized Models (Q4_K_S)**:
90
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q4_K_S/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S.gguf)
91
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q4_K_S/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S.gguf)
92
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q4_K_S/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S.gguf)
 
18
  - [Freepik's Flux.1-Lite-8B-alpha](https://huggingface.co/Freepik/flux.1-lite-8B-alpha)
19
  - [Flux-dev-de-distill](https://huggingface.co/nyanko7/flux-dev-de-distill)
20
 
21
+ Detail enhancement and acceleration techniques have been applied, particularly optimized for NVIDIA 4XXX cards (maybe 3XXX too). The goal is to have high efficiency accelerated models with lower overhead. The (de-re-destill) model can be used with CFG remaining at 1. Also the baked-in accelerators work as intended.
 
 
22
 
23
  **====================================**
24
 
 
49
  - **Best of Flux: Style Enhancing LoRA** (Weight: 0.06) ([Model Link](https://civitai.com/models/821668))
50
 
51
  **Distillation Used:**
52
+ - **Flux distilled lora** (Weight: Hyper - 0.65 | Turbo - 0.50) ([Model Link](https://civitai.com/models/977247/flux-distilled-lora))
53
+
54
+ 1. **SAFETensors Format (fp8_34m3fn_fast)**:
55
+ - [flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-Distilled-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/Lite-8B-Plus/Distilled/FP8/flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-Distilled-fp8_e4m3fn_fast-V2.safetensors)
56
+ - [flux.1-lite-8B-alpha-Hyper-16.Steps-Detail.Plus-Distilled-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/Lite-8B-Plus/Distilled/FP8/flux.1-lite-8B-alpha-Hyper-16.Steps-Detail.Plus-Distilled-fp8_e4m3fn_fast-V2.safetensors)
57
+ - [flux.1-lite-8B-alpha-Turbo-8.Steps-Detail.Plus-Distilled-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/Lite-8B-Plus/Distilled/FP8/flux.1-lite-8B-alpha-Turbo-8.Steps-Detail.Plus-Distilled-fp8_e4m3fn_fast-V2.safetensors)
58
 
59
  3. **GGUF Quantized Models (Q8_0)**:
60
  - [flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-Distilled-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/Lite-8B-Plus/Distilled/GGUF/Q8_0/flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-Distilled-V2-Q8_0.gguf)
 
74
  **Re-Distillation Used:**
75
  - **Flux distilled lora** (Weight: -1.00) ([Model Link](https://civitai.com/models/977247/flux-distilled-lora))
76
 
77
+ 2. **SAFETensors Format V2 (fp8_34m3fn_fast)**:
78
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/FP8/Version%202/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2.safetensors)
79
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/FP8/Version%202/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2.safetensors)
80
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/FP8/Version%202/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-fp8_e4m3fn_fast-V2.safetensors)
81
 
82
+ 5. **GGUF Quantized Models (Q8_0)**:
83
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q8_0/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0.gguf)
84
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q8_0/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0.gguf)
85
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q8_0/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q8_0.gguf)
86
 
87
+ 6. **GGUF Quantized Models (Q6_K)**:
88
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q6_K/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K.gguf)
89
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q6_K/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K.gguf)
90
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q6_K/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q6_K.gguf)
91
 
92
+ 7. **GGUF Quantized Models (Q4_K_S)**:
93
  - [Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q4_K_S/Flux-dev-de-re-distill-Hyper.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S.gguf)
94
  - [Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q4_K_S/Flux-dev-de-re-distill-Hyper.16.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S.gguf)
95
  - [Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S](https://huggingface.co/mdmachine/FLUX.Model.Merge-Detail.Enhancement.and.Acceleration/blob/main/de-re-distill/GGUF/Q4_K_S/Flux-dev-de-re-distill-Turbo.8.Step-Detail.Plus-ReDis-MAIN-V2-Q4_K_S.gguf)