Text-to-Image
Diffusers
lora
template:diffusion-lora
prithivMLmods commited on
Commit
86eb713
·
verified ·
1 Parent(s): 11b4bff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -4
README.md CHANGED
@@ -19,19 +19,60 @@ widget:
19
  url: images/4444.png
20
  base_model: black-forest-labs/FLUX.1-dev
21
  instance_prompt: Belle, the female character
22
-
23
  ---
 
 
 
24
  # Belle
25
 
26
  <Gallery />
 
 
27
 
 
 
 
 
 
 
 
28
 
29
- ## Trigger words
 
 
 
 
 
 
 
 
 
 
 
30
 
31
- You should use `Belle` to trigger the image generation.
32
 
33
- You should use `the female character` to trigger the image generation.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
 
 
35
 
36
  ## Download model
37
 
 
19
  url: images/4444.png
20
  base_model: black-forest-labs/FLUX.1-dev
21
  instance_prompt: Belle, the female character
 
22
  ---
23
+
24
+ ![aas.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/j8NdoW7Oxs2MEgVIG1z_F.png)
25
+
26
  # Belle
27
 
28
  <Gallery />
29
+ # Model description for Belle
30
+ Image Processing Parameters
31
 
32
+ | Parameter | Value | Parameter | Value |
33
+ |---------------------------|--------|---------------------------|--------|
34
+ | LR Scheduler | constant | Noise Offset | 0.03 |
35
+ | Optimizer | AdamW | Multires Noise Discount | 0.1 |
36
+ | Network Dim | 64 | Multires Noise Iterations | 10 |
37
+ | Network Alpha | 32 | Repeat & Steps | 18 & 2100 |
38
+ | Epoch | 21 | Save Every N Epochs | 1 |
39
 
40
+ Labeling: florence2-en(natural language & English)
41
+
42
+ Total Images Used for Training : 14
43
+
44
+ Source : Pinterest
45
+
46
+ ## Best Dimensions & Inference
47
+
48
+ | **Dimensions** | **Aspect Ratio** | **Recommendation** |
49
+ |-----------------|------------------|---------------------------|
50
+ | 1280 x 832 | 3:2 | Best |
51
+ | 1024 x 1024 | 1:1 | Default |
52
 
53
+ ### Inference Range
54
 
55
+ - **Recommended Inference Steps:** 30–35
56
+
57
+ ## Setting Up
58
+ ```python
59
+ import torch
60
+ from pipelines import DiffusionPipeline
61
+
62
+ base_model = "black-forest-labs/FLUX.1-dev"
63
+ pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
64
+
65
+ lora_repo = "strangerzonehf/Belle"
66
+ trigger_word = "Belle the female character"
67
+ pipe.load_lora_weights(lora_repo)
68
+
69
+ device = torch.device("cuda")
70
+ pipe.to(device)
71
+ ```
72
+
73
+ ## Trigger words
74
 
75
+ You should use `Belle the female character` to trigger the image generation.
76
 
77
  ## Download model
78