strkyyy commited on
Commit
c088ece
·
verified ·
1 Parent(s): fd0f778

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: openrail++
3
+ language:
4
+ - en
5
+ library_name: diffusers
6
+ pipeline_tag: text-to-image
7
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
8
+ instance_prompt: blu3prnt
9
+ tags:
10
+ - lora
11
+ - stable-diffusion-xl
12
+ - text-to-image
13
+ - diffusers
14
+ - style
15
+ - blueprint
16
+ - technical-drawing
17
+ - schematic
18
+ - drafting
19
+ - engineering
20
+ - vintage
21
+ - diagram
22
+ - orthographic-projection
23
+ - precise
24
+ - 19th-century
25
+ - 20th-century
26
+ - grid-paper
27
+ - lora
28
+ - style-lora
29
+ widget:
30
+ - text: "blu3prnt, a vintage car schematic"
31
+ - text: "blu3prnt, a fantasy sword with dimensions"
32
+ - text: "blu3prnt, a coffee machine exploded view"
33
+ ---
34
+
35
+ # Vintage Engineering Blueprint SDXL LoRA Drawing
36
+
37
+ ## What it does
38
+ This LoRA model transforms any input into a classic engineering blueprint style, featuring white technical line drawings on a deep cyan-blue background with precise orthographic projections and detailed dimension lines and labels.
39
+ ## How to use
40
+ Trigger the effect by including the word `blu3prnt` in your prompt. For best results, set the strength between 0.6 and 1.0. Use the EMA sampler for a smoother output, adjusting steps as needed to achieve clarity and detail.
41
+ ## Best for
42
+ - Vintage car schematics
43
+ - Fantasy weapon blueprints with dimensions
44
+ - Exploded view diagrams of machines like coffee makers or windmills
45
+ - Detailed cross-sections of complex machinery such as spaceships
46
+ ## Tips
47
+ Apply `blu3prnt` to inputs that require technical precision and clarity. Avoid using overly detailed prompts which may overwhelm the model's ability to render clean, simple lines.
48
+ ## Example Prompts
49
+
50
+ ```
51
+ blu3prnt --detailed portrait of an engineer in a dimly lit workshop
52
+ ```
53
+
54
+ ```
55
+ blu3prnt --modern cityscape with towering skyscrapers at dusk
56
+ ```
57
+
58
+ ```
59
+ blu3prnt --close-up of a vintage mechanical clock with intricate gears
60
+ ```
61
+
62
+ ```
63
+ blu3prnt --a robot arm performing precise assembly in a cleanroom
64
+ ```
65
+
66
+ ```
67
+ blu3prnt --calm and serene evening scene with rolling hills and trees
68
+ ```
69
+
70
+ ```
71
+ blu3prnt --abstract representation of digital circuits on grid paper
72
+ ```
73
+
74
+ ## Trigger word
75
+
76
+ Activate with `blu3prnt`. Recommended strength: **0.9**.
77
+
78
+ ## Showcase
79
+
80
+ ![showcase 1](./showcase/showcase_01.png)
81
+ ![showcase 2](./showcase/showcase_02.png)
82
+ ![showcase 3](./showcase/showcase_03.png)
83
+ ![showcase 4](./showcase/showcase_04.png)
84
+ ![showcase 5](./showcase/showcase_05.png)
85
+ ![showcase 6](./showcase/showcase_06.png)
86
+ ![showcase 7](./showcase/showcase_07.png)
87
+ ![showcase 8](./showcase/showcase_08.png)
88
+
89
+ ## Usage with `diffusers`
90
+
91
+ ```python
92
+ from diffusers import AutoPipelineForText2Image
93
+ import torch
94
+
95
+ pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
96
+ pipe.load_lora_weights("strkyyy/blueprint-technical")
97
+ image = pipe("blu3prnt, your prompt", num_inference_steps=30).images[0]
98
+ ```