Norod78 commited on
Commit
ad07eaf
·
verified ·
1 Parent(s): 2d8cdc9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -8,10 +8,10 @@ tags:
8
  - ai-toolkit
9
  widget:
10
  - text: A woman character with red hair, playing chess at the park, bomb going off
11
- in the background [trigger]
12
  output:
13
  url: samples/1725458804843__000008050_0.jpg
14
- - text: a [trigger] man character holding a coffee cup, in a beanie, sitting at
15
  a cafe
16
  output:
17
  url: samples/1725458846417__000008050_1.jpg
@@ -19,10 +19,10 @@ widget:
19
  laser lights, punk rocker FluxToon style
20
  output:
21
  url: samples/1725458887751__000008050_2.jpg
22
- - text: hipster with a beard, building a chair, in a wood shop [trigger]
23
  output:
24
  url: samples/1725458928911__000008050_3.jpg
25
- - text: '[trigger] Wonderwoman holding a sign that says ''I LOVE FluxToon!'''
26
  output:
27
  url: samples/1725458969982__000008050_4.jpg
28
  base_model: black-forest-labs/FLUX.1-dev
@@ -39,6 +39,7 @@ Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
39
  ## Trigger words
40
 
41
  You should use `FluxToon style` to trigger the image generation.
 
42
 
43
  ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
44
 
@@ -54,7 +55,7 @@ import torch
54
 
55
  pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
56
  pipeline.load_lora_weights('Norod78/FluxToon_style_flux_lora', weight_name='FluxToon_style_flux_lora')
57
- image = pipeline('A woman character with red hair, playing chess at the park, bomb going off in the background [trigger]').images[0]
58
  image.save("my_image.png")
59
  ```
60
 
 
8
  - ai-toolkit
9
  widget:
10
  - text: A woman character with red hair, playing chess at the park, bomb going off
11
+ in the background FluxToon style
12
  output:
13
  url: samples/1725458804843__000008050_0.jpg
14
+ - text: a FluxToon style man character holding a coffee cup, in a beanie, sitting at
15
  a cafe
16
  output:
17
  url: samples/1725458846417__000008050_1.jpg
 
19
  laser lights, punk rocker FluxToon style
20
  output:
21
  url: samples/1725458887751__000008050_2.jpg
22
+ - text: hipster with a beard, building a chair, in a wood shop FluxToon style
23
  output:
24
  url: samples/1725458928911__000008050_3.jpg
25
+ - text: 'FluxToon style Wonderwoman holding a sign that says ''I LOVE FluxToon!'''
26
  output:
27
  url: samples/1725458969982__000008050_4.jpg
28
  base_model: black-forest-labs/FLUX.1-dev
 
39
  ## Trigger words
40
 
41
  You should use `FluxToon style` to trigger the image generation.
42
+ When describing people, adding the word 'character' helps (e.g. 'a woman character', 'a group of characters' and so on)
43
 
44
  ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
45
 
 
55
 
56
  pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
57
  pipeline.load_lora_weights('Norod78/FluxToon_style_flux_lora', weight_name='FluxToon_style_flux_lora')
58
+ image = pipeline('A woman character with red hair, playing chess at the park, bomb going off in the background FluxToon style').images[0]
59
  image.save("my_image.png")
60
  ```
61