lichorosario
commited on
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: flux-1-dev-non-commercial-license
|
4 |
+
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
tags:
|
8 |
+
- flux
|
9 |
+
- diffusers
|
10 |
+
- lora
|
11 |
+
base_model: black-forest-labs/FLUX.1-schnell
|
12 |
+
pipeline_tag: text-to-image
|
13 |
+
library_name: diffusers
|
14 |
+
inference:
|
15 |
+
parameters:
|
16 |
+
width: 1024
|
17 |
+
height: 1024
|
18 |
+
widget:
|
19 |
+
- text: >-
|
20 |
+
This is a digital cartoon illustration that portrays a character reminiscent
|
21 |
+
of a horror or dark fantasy figure. The central figure is a pale, human-like
|
22 |
+
face with an eerie, menacing expression. The character's skin is stark
|
23 |
+
white, creating a ghostly appearance, and is crisscrossed with red lines
|
24 |
+
forming a grid pattern on the head. At each intersection of the grid, there
|
25 |
+
are metal nails or pins, all protruding outward in a symmetrical fashion,
|
26 |
+
emphasizing a mechanical or tortured aesthetic. The eyes are dark and
|
27 |
+
sunken with heavy, dark red and black shading around them, creating an
|
28 |
+
ominous stare. The character's mouth is open, revealing sharp teeth with a
|
29 |
+
distinct gap between the top and bottom sets, further adding to the
|
30 |
+
unsettling look. The nose is thin, with blue-tinted shadows around it,
|
31 |
+
enhancing the cold, inhuman feel of the face. The figure is dressed in
|
32 |
+
black, with only the high collar visible, further isolating the attention on
|
33 |
+
the face and head. The background is a gradient of dark gray to black, which
|
34 |
+
contributes to the foreboding tone of the image. The overall style uses
|
35 |
+
clean, solid lines and smooth gradients, typical of modern vector art, but
|
36 |
+
the subject matter and atmosphere are much darker and gothic compared to
|
37 |
+
typical cartoon illustrations. The image draws upon visual cues from horror
|
38 |
+
characters, using sharp contrast, exaggerated facial features, and
|
39 |
+
symmetrical patterns to evoke unease. The pins and grid pattern across the
|
40 |
+
head give it a painful and torturous look, likely referencing themes of body
|
41 |
+
modification or mechanical horror.
|
42 |
+
output:
|
43 |
+
url: images/example_7s5wa1khf.png
|
44 |
+
|
45 |
+
---
|
46 |
+
|
47 |
+
# Tosti vector full captions
|
48 |
+
Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `tostiok`.
|
49 |
+
|
50 |
+
|
51 |
+
## Trigger words
|
52 |
+
tosti vector style
|
53 |
+
<Gallery />
|
54 |
+
|
55 |
+
|
56 |
+
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
|
57 |
+
|
58 |
+
```py
|
59 |
+
from diffusers import AutoPipelineForText2Image
|
60 |
+
import torch
|
61 |
+
|
62 |
+
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
|
63 |
+
pipeline.load_lora_weights('lichorosario/flux-samhtr-remastered', weight_name='lora.safetensors')
|
64 |
+
image = pipeline('your prompt').images[0]
|
65 |
+
```
|
66 |
+
|
67 |
+
|
68 |
+
|
69 |
+
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|