Model card auto-generated by SimpleTuner
Browse files
README.md
ADDED
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: "black-forest-labs/FLUX.1-dev"
|
4 |
+
tags:
|
5 |
+
- flux
|
6 |
+
- flux-diffusers
|
7 |
+
- text-to-image
|
8 |
+
- diffusers
|
9 |
+
- simpletuner
|
10 |
+
- lora
|
11 |
+
- template:sd-lora
|
12 |
+
inference: true
|
13 |
+
widget:
|
14 |
+
- text: 'unconditional (blank prompt)'
|
15 |
+
parameters:
|
16 |
+
negative_prompt: 'blurry, cropped, ugly'
|
17 |
+
output:
|
18 |
+
url: ./assets/image_0_0.png
|
19 |
+
- text: 'unconditional (blank prompt)'
|
20 |
+
parameters:
|
21 |
+
negative_prompt: 'blurry, cropped, ugly'
|
22 |
+
output:
|
23 |
+
url: ./assets/image_1_1.png
|
24 |
+
- text: 'A bustling kitchen scene with three chefs in white uniforms and tall hats. The chef in the foreground, a woman with her hair in a tight bun, is pointing emphatically at a large pot on the stove with her right index finger. Her left hand holds a wooden spoon, and her expression is one of intense concentration. To her right, a male chef is chopping vegetables on a cutting board, but his head is turned towards where his colleague is pointing. In the background, the third chef is reaching up to a high shelf, pointing with his left hand at a specific spice jar. Steam rises from several pots on the industrial stove, and stainless steel appliances gleam in the bright kitchen lighting. The scene conveys a sense of urgency and coordination in a professional kitchen environment.'
|
25 |
+
parameters:
|
26 |
+
negative_prompt: 'blurry, cropped, ugly'
|
27 |
+
output:
|
28 |
+
url: ./assets/image_2_0.png
|
29 |
+
- text: 'A bustling kitchen scene with three chefs in white uniforms and tall hats. The chef in the foreground, a woman with her hair in a tight bun, is pointing emphatically at a large pot on the stove with her right index finger. Her left hand holds a wooden spoon, and her expression is one of intense concentration. To her right, a male chef is chopping vegetables on a cutting board, but his head is turned towards where his colleague is pointing. In the background, the third chef is reaching up to a high shelf, pointing with his left hand at a specific spice jar. Steam rises from several pots on the industrial stove, and stainless steel appliances gleam in the bright kitchen lighting. The scene conveys a sense of urgency and coordination in a professional kitchen environment.'
|
30 |
+
parameters:
|
31 |
+
negative_prompt: 'blurry, cropped, ugly'
|
32 |
+
output:
|
33 |
+
url: ./assets/image_3_1.png
|
34 |
+
---
|
35 |
+
|
36 |
+
# pointerpointer-v1
|
37 |
+
|
38 |
+
This is a standard PEFT LoRA derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev).
|
39 |
+
|
40 |
+
|
41 |
+
The main validation prompt used during training was:
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
```
|
46 |
+
A bustling kitchen scene with three chefs in white uniforms and tall hats. The chef in the foreground, a woman with her hair in a tight bun, is pointing emphatically at a large pot on the stove with her right index finger. Her left hand holds a wooden spoon, and her expression is one of intense concentration. To her right, a male chef is chopping vegetables on a cutting board, but his head is turned towards where his colleague is pointing. In the background, the third chef is reaching up to a high shelf, pointing with his left hand at a specific spice jar. Steam rises from several pots on the industrial stove, and stainless steel appliances gleam in the bright kitchen lighting. The scene conveys a sense of urgency and coordination in a professional kitchen environment.
|
47 |
+
```
|
48 |
+
|
49 |
+
## Validation settings
|
50 |
+
- CFG: `3.0`
|
51 |
+
- CFG Rescale: `0.0`
|
52 |
+
- Steps: `25`
|
53 |
+
- Sampler: `None`
|
54 |
+
- Seed: `42`
|
55 |
+
- Resolutions: `1024x1024,832x1216`
|
56 |
+
|
57 |
+
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
|
58 |
+
|
59 |
+
You can find some example images in the following gallery:
|
60 |
+
|
61 |
+
|
62 |
+
<Gallery />
|
63 |
+
|
64 |
+
The text encoder **was not** trained.
|
65 |
+
You may reuse the base model text encoder for inference.
|
66 |
+
|
67 |
+
|
68 |
+
## Training settings
|
69 |
+
|
70 |
+
- Training epochs: 3
|
71 |
+
- Training steps: 100
|
72 |
+
- Learning rate: 0.0002
|
73 |
+
- Effective batch size: 90
|
74 |
+
- Micro-batch size: 45
|
75 |
+
- Gradient accumulation steps: 2
|
76 |
+
- Number of GPUs: 1
|
77 |
+
- Prediction type: flow-matching
|
78 |
+
- Rescaled betas zero SNR: False
|
79 |
+
- Optimizer: adamw_bf16
|
80 |
+
- Precision: bf16
|
81 |
+
- Quantised: No
|
82 |
+
- Xformers: Not used
|
83 |
+
- LoRA Rank: 16
|
84 |
+
- LoRA Alpha: None
|
85 |
+
- LoRA Dropout: 0.1
|
86 |
+
- LoRA initialisation style: default
|
87 |
+
|
88 |
+
|
89 |
+
## Datasets
|
90 |
+
|
91 |
+
### pointerpointer
|
92 |
+
- Repeats: 0
|
93 |
+
- Total number of images: 711
|
94 |
+
- Total number of aspect buckets: 1
|
95 |
+
- Resolution: 0.262144 megapixels
|
96 |
+
- Cropped: True
|
97 |
+
- Crop style: center
|
98 |
+
- Crop aspect: square
|
99 |
+
|
100 |
+
|
101 |
+
## Inference
|
102 |
+
|
103 |
+
|
104 |
+
```python
|
105 |
+
import torch
|
106 |
+
from diffusers import DiffusionPipeline
|
107 |
+
|
108 |
+
model_id = 'black-forest-labs/FLUX.1-dev'
|
109 |
+
adapter_id = 'MaheshNat/pointerpointer-v1'
|
110 |
+
pipeline = DiffusionPipeline.from_pretrained(model_id)
|
111 |
+
pipeline.load_lora_weights(adapter_id)
|
112 |
+
|
113 |
+
prompt = "A bustling kitchen scene with three chefs in white uniforms and tall hats. The chef in the foreground, a woman with her hair in a tight bun, is pointing emphatically at a large pot on the stove with her right index finger. Her left hand holds a wooden spoon, and her expression is one of intense concentration. To her right, a male chef is chopping vegetables on a cutting board, but his head is turned towards where his colleague is pointing. In the background, the third chef is reaching up to a high shelf, pointing with his left hand at a specific spice jar. Steam rises from several pots on the industrial stove, and stainless steel appliances gleam in the bright kitchen lighting. The scene conveys a sense of urgency and coordination in a professional kitchen environment."
|
114 |
+
|
115 |
+
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
|
116 |
+
image = pipeline(
|
117 |
+
prompt=prompt,
|
118 |
+
num_inference_steps=25,
|
119 |
+
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
|
120 |
+
width=1024,
|
121 |
+
height=1024,
|
122 |
+
guidance_scale=3.0,
|
123 |
+
).images[0]
|
124 |
+
image.save("output.png", format="PNG")
|
125 |
+
```
|
126 |
+
|