prithivMLmods
commited on
Commit
•
57f44a0
1
Parent(s):
f89feb5
Update README.md
Browse files
README.md
CHANGED
@@ -4,17 +4,45 @@ tags:
|
|
4 |
- lora
|
5 |
- diffusers
|
6 |
- template:diffusion-lora
|
|
|
|
|
|
|
7 |
widget:
|
8 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
output:
|
10 |
url: images/111.png
|
11 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
12 |
output:
|
13 |
url: images/222.png
|
14 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
output:
|
16 |
url: images/333.png
|
17 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
output:
|
19 |
url: images/444.png
|
20 |
base_model: black-forest-labs/FLUX.1-dev
|
@@ -25,15 +53,55 @@ license: creativeml-openrail-m
|
|
25 |
|
26 |
<Gallery />
|
27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
|
30 |
## Trigger words
|
31 |
|
32 |
You should use `3DXLP3` to trigger the image generation.
|
33 |
|
34 |
-
|
35 |
## Download model
|
36 |
|
37 |
Weights for this model are available in Safetensors format.
|
38 |
|
39 |
-
[Download](/strangerzonehf/Flux-3DXL-Partfile-0003/tree/main) them in the Files & versions tab.
|
|
|
4 |
- lora
|
5 |
- diffusers
|
6 |
- template:diffusion-lora
|
7 |
+
- 3DXL
|
8 |
+
- Flux
|
9 |
+
- Character-3D
|
10 |
widget:
|
11 |
+
- text: >-
|
12 |
+
3DXLP3, a vibrant red womans face is adorned with a black collar and a black
|
13 |
+
shirt. Her hair is a vibrant shade of red, adding a pop of color to her
|
14 |
+
face. Her eyes are a piercing blue, and her eyebrows are a darker shade of
|
15 |
+
brown. Her lips are a lighter shade of pink, and she is smiling slightly at
|
16 |
+
the moment. The backdrop is a dark gray, creating a stark contrast to her
|
17 |
+
red dress.
|
18 |
output:
|
19 |
url: images/111.png
|
20 |
+
- text: >-
|
21 |
+
3DXLP3, a man dressed in a black jacket, white shirt, black tie, and a blue
|
22 |
+
vest with a black belt. He is holding a black gun in his right hand, aiming
|
23 |
+
it towards the right side of the frame. His hair is short and dark brown,
|
24 |
+
and he has a serious expression on his face. The backdrop is a light gray,
|
25 |
+
and the mans shadow is cast on the left side of his chest.
|
26 |
output:
|
27 |
url: images/222.png
|
28 |
+
- text: >-
|
29 |
+
3DXLP3, a 3D rendering of a muscular man stands in front of a gray backdrop.
|
30 |
+
He is dressed in a red headband, white wrist bands, and a pair of yellow
|
31 |
+
sunglasses. His left arm is raised in the air, while his right arm is bent
|
32 |
+
at the elbow. His right hand is resting on his hip, and his left hand is
|
33 |
+
positioned in a way that he is pointing to the left. He has a beard,
|
34 |
+
mustache, and dark hair, and is wearing a red and yellow swimsuit with white
|
35 |
+
stars on the bottom. His legs are covered in a light-colored pair of socks,
|
36 |
+
and the socks are a bright yellow color
|
37 |
output:
|
38 |
url: images/333.png
|
39 |
+
- text: >-
|
40 |
+
3DXLP3, A close-up shot of a black mans face, positioned in front of a gray
|
41 |
+
backdrop. He is wearing a blue baseball cap with a white number 3
|
42 |
+
embroidered on the front of the cap. His earrings are adorned with silver
|
43 |
+
earrings. His mouth is slightly open, with a black mustache and beard. His
|
44 |
+
eyebrows are dark and goatee, adding a touch of texture to his face. He is
|
45 |
+
wearing a dark blue t-shirt with a collar.
|
46 |
output:
|
47 |
url: images/444.png
|
48 |
base_model: black-forest-labs/FLUX.1-dev
|
|
|
53 |
|
54 |
<Gallery />
|
55 |
|
56 |
+
## Model description for 3DXL Partfile 0003
|
57 |
+
|
58 |
+
Image Processing Parameters
|
59 |
+
|
60 |
+
| Parameter | Value | Parameter | Value |
|
61 |
+
|---------------------------|--------|---------------------------|--------|
|
62 |
+
| LR Scheduler | constant | Noise Offset | 0.03 |
|
63 |
+
| Optimizer | AdamW | Multires Noise Discount | 0.1 |
|
64 |
+
| Network Dim | 64 | Multires Noise Iterations | 10 |
|
65 |
+
| Network Alpha | 32 | Repeat & Steps | 20 & 2800 |
|
66 |
+
| Epoch | 20 | Save Every N Epochs | 1 |
|
67 |
+
|
68 |
+
Labeling: florence2-en(natural language & English)
|
69 |
+
|
70 |
+
Total Images Used for Training : 15
|
71 |
+
|
72 |
+
## Best Dimensions & Inference
|
73 |
+
|
74 |
+
| **Dimensions** | **Aspect Ratio** | **Recommendation** |
|
75 |
+
|-----------------|------------------|---------------------------|
|
76 |
+
| 1280 x 832 | 3:2 | Best |
|
77 |
+
| 1024 x 1024 | 1:1 | Default |
|
78 |
+
|
79 |
+
### Inference Range
|
80 |
+
- **Recommended Inference Steps:** 30–35
|
81 |
+
|
82 |
+
## Setting Up
|
83 |
+
```python
|
84 |
+
import torch
|
85 |
+
from pipelines import DiffusionPipeline
|
86 |
+
|
87 |
+
base_model = "black-forest-labs/FLUX.1-dev"
|
88 |
+
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
|
89 |
+
|
90 |
+
lora_repo = "strangerzonehf/Flux-3DXL-Partfile-0003"
|
91 |
+
trigger_word = "3DXLP3"
|
92 |
+
pipe.load_lora_weights(lora_repo)
|
93 |
+
|
94 |
+
device = torch.device("cuda")
|
95 |
+
pipe.to(device)
|
96 |
+
```
|
97 |
|
98 |
|
99 |
## Trigger words
|
100 |
|
101 |
You should use `3DXLP3` 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-3DXL-Partfile-0003/tree/main) them in the Files & versions tab.
|