Text-to-Image
Diffusers
Safetensors
LibreFluxControlNetPipeline
neuralvfx commited on
Commit
ae44ce7
·
verified ·
1 Parent(s): 6a25168

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -10,14 +10,12 @@ base_model: jimmycarter/LibreFLUX
10
  ![Example: Control image vs result](examples/side_by_side_b.png)
11
 
12
  # Fun Facts
13
- - I built this repo to train the model: [https://github.com/NeuralVFX/LibreFLUX-ControlNet](https://github.com/NeuralVFX/LibreFLUX-ControlNet)
14
- - This ControlNet is trained exclusively on images generated by [Segment Anything (SAM)](https://aidemos.meta.com/segment-anything/)
15
  - Uses SAM style images as input, outputs photorealistic images
16
  - Trained at 1024x1024 resolution, inference works best at 1.5k and up
17
  - Trained on 320K segmented images from [laion2b-squareish-1536px](https://huggingface.co/datasets/opendiffusionai/laion2b-squareish-1536px)
18
- - Base transformer model used: [https://huggingface.co/jimmycarter/LibreFlux-SimpleTuner](https://huggingface.co/jimmycarter/LibreFlux-SimpleTuner)
19
- - Inference code roughly adapted from: [https://github.com/bghira/SimpleTuner](https://github.com/bghira/SimpleTuner)
20
-
21
 
22
  # Showcases
23
  <table style="width:100%; table-layout:fixed;">
@@ -36,11 +34,13 @@ base_model: jimmycarter/LibreFLUX
36
  </table>
37
 
38
 
39
- # How does this relate to LibreFLUX?
40
- - Base model is [LibreFLUX](https://huggingface.co/jimmycarter/LibreFLUX)
41
  - Trained in same non-distilled fashion
42
  - Uses Attention Masking
43
- - Uses CFG during Inference
 
 
44
 
45
  # Compatibility
46
  ```py
 
10
  ![Example: Control image vs result](examples/side_by_side_b.png)
11
 
12
  # Fun Facts
13
+ - Trained exclusively on images generated by [Segment Anything (SAM)](https://aidemos.meta.com/segment-anything/)
 
14
  - Uses SAM style images as input, outputs photorealistic images
15
  - Trained at 1024x1024 resolution, inference works best at 1.5k and up
16
  - Trained on 320K segmented images from [laion2b-squareish-1536px](https://huggingface.co/datasets/opendiffusionai/laion2b-squareish-1536px)
17
+ - Base model is [LibreFLUX](https://huggingface.co/jimmycarter/LibreFLUX)
18
+
 
19
 
20
  # Showcases
21
  <table style="width:100%; table-layout:fixed;">
 
34
  </table>
35
 
36
 
37
+ # Extra Details
38
+ - I built this repo to train the model: [https://github.com/NeuralVFX/LibreFLUX-ControlNet](https://github.com/NeuralVFX/LibreFLUX-ControlNet)
39
  - Trained in same non-distilled fashion
40
  - Uses Attention Masking
41
+ - Uses CFG during Inference ( allows negative prompting )
42
+ - Inference code roughly adapted from: [https://github.com/bghira/SimpleTuner](https://github.com/bghira/SimpleTuner)
43
+
44
 
45
  # Compatibility
46
  ```py