prithivMLmods
commited on
Commit
•
563cca4
1
Parent(s):
73bc55e
Update README.md
Browse files
README.md
CHANGED
@@ -4,35 +4,104 @@ tags:
|
|
4 |
- lora
|
5 |
- diffusers
|
6 |
- template:diffusion-lora
|
|
|
7 |
widget:
|
8 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
output:
|
10 |
url: images/1.png
|
11 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
output:
|
13 |
url: images/3.png
|
14 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
output:
|
16 |
url: images/2.png
|
17 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
output:
|
19 |
url: images/4.png
|
20 |
base_model: black-forest-labs/FLUX.1-dev
|
21 |
instance_prompt: Claymation
|
22 |
license: creativeml-openrail-m
|
23 |
---
|
24 |
-
|
25 |
|
26 |
<Gallery />
|
27 |
|
|
|
28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
## Trigger words
|
30 |
|
31 |
You should use `Claymation` to trigger the image generation.
|
32 |
|
33 |
-
|
34 |
## Download model
|
35 |
|
36 |
Weights for this model are available in Safetensors format.
|
37 |
|
38 |
-
[Download](/strangerzonehf/Flux-Claymation-XC-LoRA/tree/main) them in the Files & versions tab.
|
|
|
4 |
- lora
|
5 |
- diffusers
|
6 |
- template:diffusion-lora
|
7 |
+
- Claymation
|
8 |
widget:
|
9 |
+
- text: >-
|
10 |
+
Claymation, Captured from a high-angle perspective on a vibrant yellow
|
11 |
+
backdrop, a medium-sized cartoon monkey is posed in front of the viewer. The
|
12 |
+
monkey is adorned with a brown head, a brown vest, and brown pants. Its arms
|
13 |
+
are draped over its chest, adding a touch of balance to the scene. A yellow
|
14 |
+
bottle with a yellow label, adorned with the word "MONKEY" is positioned to
|
15 |
+
the left of the monkey, positioned in a way that creates a stark contrast to
|
16 |
+
the monkeys body. The bottles cap, a yellowish-orange color, adds a pop of
|
17 |
+
color to the composition. Three bananas are arranged to the bottom right
|
18 |
+
corner of the frame.
|
19 |
output:
|
20 |
url: images/1.png
|
21 |
+
- text: >-
|
22 |
+
Claymation, a small cartoon figure stands against a stark white backdrop.
|
23 |
+
The figures face is adorned with a black t-shirt, gray shorts, black shoes,
|
24 |
+
and a pair of white socks. The head of the figure is adorned in a light
|
25 |
+
brown beanie with a white patch on it that reads "KUBO". The figure is
|
26 |
+
holding a wooden baseball bat in its left hand, with the word "OKUBO"
|
27 |
+
written on it in black.
|
28 |
output:
|
29 |
url: images/3.png
|
30 |
+
- text: >-
|
31 |
+
Claymation, a medium-sized cartoon figure stands against a stark yellow
|
32 |
+
backdrop. The figures head is adorned with a gold crown, adorned with small
|
33 |
+
gold dots, adding a pop of color to the scene. Its eyes are wide open,
|
34 |
+
revealing a glimpse of black eyebrows and black eyelashes. Its head is
|
35 |
+
encircled by a gold ribbon, adding depth to the composition. Its outfit is
|
36 |
+
adorned in a cream-colored dress with a brown belt, adding to the overall
|
37 |
+
composition.
|
38 |
output:
|
39 |
url: images/2.png
|
40 |
+
- text: >-
|
41 |
+
Claymation, a small cartoon figure stands against a stark white backdrop.
|
42 |
+
The figures face is adorned with black eyes, a black headband, and a pair of
|
43 |
+
red shorts with a white belt tied around the waist. The word "KUBO" is
|
44 |
+
written in black letters on the chest of the figure, along with the word
|
45 |
+
"UBO" in a smaller font. A life preserver is in its right hand, adding a
|
46 |
+
touch of color to the figure.
|
47 |
output:
|
48 |
url: images/4.png
|
49 |
base_model: black-forest-labs/FLUX.1-dev
|
50 |
instance_prompt: Claymation
|
51 |
license: creativeml-openrail-m
|
52 |
---
|
53 |
+
![clay.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/RQ7BhPk1nGo03cOTCxoKC.png)
|
54 |
|
55 |
<Gallery />
|
56 |
|
57 |
+
## Model description for Flux-Ghibli-Art-LoRA
|
58 |
|
59 |
+
Image Processing Parameters
|
60 |
+
|
61 |
+
| Parameter | Value | Parameter | Value |
|
62 |
+
|---------------------------|--------|---------------------------|--------|
|
63 |
+
| LR Scheduler | constant | Noise Offset | 0.03 |
|
64 |
+
| Optimizer | AdamW | Multires Noise Discount | 0.1 |
|
65 |
+
| Network Dim | 64 | Multires Noise Iterations | 10 |
|
66 |
+
| Network Alpha | 32 | Repeat & Steps | 16 & 2000 |
|
67 |
+
| Epoch | 10 | Save Every N Epochs | 1 |
|
68 |
+
|
69 |
+
Labeling: florence2-en(natural language & English)
|
70 |
+
|
71 |
+
Total Images Used for Training : 17
|
72 |
+
|
73 |
+
## Best Dimensions & Inference
|
74 |
+
|
75 |
+
| **Dimensions** | **Aspect Ratio** | **Recommendation** |
|
76 |
+
|-----------------|------------------|---------------------------|
|
77 |
+
| 1280 x 832 | 3:2 | Best |
|
78 |
+
| 1024 x 1024 | 1:1 | Default |
|
79 |
+
|
80 |
+
### Inference Range
|
81 |
+
|
82 |
+
- **Recommended Inference Steps:** 30–35
|
83 |
+
|
84 |
+
## Setting Up
|
85 |
+
```python
|
86 |
+
import torch
|
87 |
+
from pipelines import DiffusionPipeline
|
88 |
+
|
89 |
+
base_model = "black-forest-labs/FLUX.1-dev"
|
90 |
+
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
|
91 |
+
|
92 |
+
lora_repo = "strangerzonehf/Flux-Claymation-XC-LoRA"
|
93 |
+
trigger_word = "Claymation"
|
94 |
+
pipe.load_lora_weights(lora_repo)
|
95 |
+
|
96 |
+
device = torch.device("cuda")
|
97 |
+
pipe.to(device)
|
98 |
+
```
|
99 |
## Trigger words
|
100 |
|
101 |
You should use `Claymation` to trigger the image generation.
|
102 |
|
|
|
103 |
## Download model
|
104 |
|
105 |
Weights for this model are available in Safetensors format.
|
106 |
|
107 |
+
[Download](/strangerzonehf/Flux-Claymation-XC-LoRA/tree/main) them in the Files & versions tab.
|