Hugging Face's logo

second-state
/
FLUX.1-schnell-GGUF

Text-to-Image
GGUF
English
image-generation
flux
Model card Files Community
apepkuss79 commited on
Commit
04f6cc1
•
1 Parent(s): aedec04

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +70 -54
README.md CHANGED
@@ -1,55 +1,71 @@
1
- ---
2
- base_model: black-forest-labs/FLUX.1-schnell
3
- license: apache-2.0
4
- model_creator: black-forest-labs
5
- model_name: FLUX.1-schnell
6
- quantized_by: Second State Inc.
7
- language:
8
- - en
9
- tags:
10
- - text-to-image
11
- - image-generation
12
- - flux
13
- ---
14
-
15
- <!-- header start -->
16
- <!-- 200823 -->
17
- <div style="width: auto; margin-left: auto; margin-right: auto">
18
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
- </div>
20
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
21
- <!-- header end -->
22
-
23
- # FLUX.1-schnell-GGUF
24
-
25
- ## Original Model
26
-
27
- [black-forest-labs/FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell)
28
-
29
- ## Run with `sd-api-server`
30
-
31
- Go to the [sd-api-server](https://github.com/LlamaEdge/sd-api-server/blob/main/README.md) repository for more information.
32
-
33
- ## Quantized GGUF Models
34
-
35
- | Name | Quant method | Bits | Size | Use case |
36
- | ---- | ---- | ---- | ---- | ----- |
37
- | [ae-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/ae-f16.gguf) | f16 | 16 | 168 MB | |
38
- | [clip_l-Q8_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/clip_l-Q8_0.gguf) | Q8_0 | 8 | 131 MB | |
39
- | [clip_l-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/clip_l-f16.gguf) | f16 | 16 | 246 MB | |
40
- | [flux1-schnell-Q4_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q4_0 | 4 | 6.69 GB | |
41
- | [flux1-schnell-Q4_1.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q4_1 | 4 | 6.69 GB | |
42
- | [flux1-schnell-Q5_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q5_0 | 5 | 6.69 GB | |
43
- | [flux1-schnell-Q5_1.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q5_1 | 5 | 6.69 GB | |
44
- | [flux1-schnell-Q8_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q8_0 | 8 | 6.69 GB | |
45
- | [flux1-schnell-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | f16 | 16 | 6.69 GB | |
46
- | [t5xxl-Q2_K.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q2_K.gguf) | Q2_K | 2 | 1.61 GB | |
47
- | [t5xxl-Q3_K.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q3_K.gguf) | Q3_K | 3 | 2.10 GB | |
48
- | [t5xxl-Q4_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q4_0.gguf) | Q4_0 | 4 | 2.75 GB | |
49
- | [t5xxl-Q4_K.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q4_K.gguf) | Q4_K | 4 | 2.75 GB | |
50
- | [t5xxl-Q5_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q5_0.gguf) | Q5_0 | 5 | 3.36 GB | |
51
- | [t5xxl-Q5_1.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q5_1.gguf) | Q5_1 | 5 | 3.67 GB | |
52
- | [t5xxl-Q8_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q8_0.gguf) | Q8_0 | 8 | 5.20 GB | |
53
- | [t5xxl-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-f16.gguf) | f16 | 16 | 9.79 GB | |
54
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  **Quantized with stable-diffusion.cpp `master-64d231f`.**
 
1
+ ---
2
+ base_model: black-forest-labs/FLUX.1-schnell
3
+ license: apache-2.0
4
+ model_creator: black-forest-labs
5
+ model_name: FLUX.1-schnell
6
+ quantized_by: Second State Inc.
7
+ language:
8
+ - en
9
+ tags:
10
+ - text-to-image
11
+ - image-generation
12
+ - flux
13
+ ---
14
+
15
+ <!-- header start -->
16
+ <!-- 200823 -->
17
+ <div style="width: auto; margin-left: auto; margin-right: auto">
18
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
+ </div>
20
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
21
+ <!-- header end -->
22
+
23
+ # FLUX.1-schnell-GGUF
24
+
25
+ ## Original Model
26
+
27
+ [black-forest-labs/FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell)
28
+
29
+ ## Run with `sd-api-server`
30
+
31
+ <!-- Go to the [sd-api-server](https://github.com/LlamaEdge/sd-api-server/blob/main/README.md) repository for more information. -->
32
+
33
+ - sd-api-server version: coming soon
34
+
35
+ - Run as LlamaEdge service
36
+
37
+ ```bash
38
+ wasmedge --dir .:. sd-api-server.wasm \
39
+ --model-name flux1-schnell \
40
+ --diffusion-model flux1-schnell-Q4_0.gguf \
41
+ --vae ae-f16.gguf \
42
+ -clip-l clip_l-f16.gguf \
43
+ --t5xxl t5xxl-Q4_0.gguf
44
+ ```
45
+
46
+ ## Quantized GGUF Models
47
+
48
+ | Name | Quant method | Bits | Size | Use case |
49
+ | ---- | ---- | ---- | ---- | ----- |
50
+ | [ae-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/ae-f16.gguf) | f16 | 16 | 168 MB | |
51
+ | [ae.safetensors](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/ae.safetensors) | f16 | 16 | 168 MB | |
52
+ | [clip_l-Q8_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/clip_l-Q8_0.gguf) | Q8_0 | 8 | 131 MB | |
53
+ | [clip_l-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/clip_l-f16.gguf) | f16 | 16 | 246 MB | |
54
+ | [clip_l.safetensors](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/clip_l.safetensors) | f16 | 16 | 246 MB | |
55
+ | [flux1-schnell-Q4_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q4_0 | 4 | 6.69 GB | |
56
+ | [flux1-schnell-Q4_1.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q4_1 | 4 | 7.43 GB | |
57
+ | [flux1-schnell-Q5_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q5_0 | 5 | 8.18 GB | |
58
+ | [flux1-schnell-Q5_1.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q5_1 | 5 | 8.92 GB | |
59
+ | [flux1-schnell-Q8_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | Q8_0 | 8 | 12.6 GB | |
60
+ | [flux1-schnell-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/flux1-schnell-Q4_0.gguf) | f16 | 16 | 23.8 GB | |
61
+ | [t5xxl-Q2_K.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q2_K.gguf) | Q2_K | 2 | 1.61 GB | |
62
+ | [t5xxl-Q3_K.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q3_K.gguf) | Q3_K | 3 | 2.10 GB | |
63
+ | [t5xxl-Q4_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q4_0.gguf) | Q4_0 | 4 | 2.75 GB | |
64
+ | [t5xxl-Q4_K.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q4_K.gguf) | Q4_K | 4 | 2.75 GB | |
65
+ | [t5xxl-Q5_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q5_0.gguf) | Q5_0 | 5 | 3.36 GB | |
66
+ | [t5xxl-Q5_1.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q5_1.gguf) | Q5_1 | 5 | 3.67 GB | |
67
+ | [t5xxl-Q8_0.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-Q8_0.gguf) | Q8_0 | 8 | 5.20 GB | |
68
+ | [t5xxl-f16.gguf](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl-f16.gguf) | f16 | 16 | 9.79 GB | |
69
+ | [t5xxl_fp16.safetensors](https://huggingface.co/second-state/FLUX.1-schnell-GGUF/blob/main/t5xxl_fp16.safetensors) | f16 | 16 | 9.79 GB | |
70
+
71
  **Quantized with stable-diffusion.cpp `master-64d231f`.**