Upload folder using huggingface_hub
Browse files- README.md +56 -27
- __init__.py +3 -0
- config.json +25 -1
- pipeline.py +75 -48
- requirements.txt +5 -26
README.md
CHANGED
@@ -1,32 +1,34 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
tags:
|
4 |
- text-to-image
|
5 |
- diffusers
|
6 |
- vector-graphics
|
7 |
- svg
|
8 |
- sketch
|
9 |
-
|
|
|
|
|
10 |
---
|
11 |
|
12 |
# DiffSketcher
|
13 |
|
14 |
-
This is a Hugging Face implementation of [DiffSketcher
|
15 |
|
16 |
## Model Description
|
17 |
|
18 |
-
DiffSketcher is a novel approach
|
19 |
|
20 |
## Usage
|
21 |
|
|
|
|
|
22 |
```python
|
23 |
from diffusers import DiffusionPipeline
|
24 |
|
25 |
-
# Load the pipeline
|
26 |
pipeline = DiffusionPipeline.from_pretrained("jree423/diffsketcher")
|
27 |
-
|
28 |
-
# Generate a vector sketch
|
29 |
-
result = pipeline(
|
30 |
prompt="A beautiful sunset over the mountains",
|
31 |
negative_prompt="ugly, blurry",
|
32 |
num_paths=96,
|
@@ -37,38 +39,65 @@ result = pipeline(
|
|
37 |
seed=42
|
38 |
)
|
39 |
|
40 |
-
# Access the SVG
|
41 |
-
|
42 |
-
|
|
|
|
|
43 |
|
44 |
# Save the SVG
|
45 |
-
with open("
|
46 |
-
f.write(
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
-
|
49 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
```
|
51 |
|
52 |
## Parameters
|
53 |
|
54 |
-
- `prompt` (str): The text prompt to guide the sketch generation
|
55 |
-
- `negative_prompt` (str, optional):
|
56 |
-
- `num_paths` (int,
|
57 |
-
- `token_ind` (int,
|
58 |
-
- `num_iter` (int,
|
59 |
-
- `guidance_scale` (float,
|
60 |
-
- `width` (float,
|
61 |
-
- `seed` (int, optional): Random seed for reproducibility
|
62 |
-
|
63 |
-
|
|
|
|
|
64 |
|
65 |
## Citation
|
66 |
|
67 |
```bibtex
|
68 |
@article{xing2023diffsketcher,
|
69 |
title={DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models},
|
70 |
-
author={Xing, Ximing and Xie, Chuang and
|
71 |
journal={arXiv preprint arXiv:2306.14685},
|
72 |
year={2023}
|
73 |
}
|
74 |
-
```
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
base_model: runwayml/stable-diffusion-v1-5
|
4 |
tags:
|
5 |
- text-to-image
|
6 |
- diffusers
|
7 |
- vector-graphics
|
8 |
- svg
|
9 |
- sketch
|
10 |
+
- stable-diffusion
|
11 |
+
pipeline_tag: text-to-image
|
12 |
+
inference: true
|
13 |
---
|
14 |
|
15 |
# DiffSketcher
|
16 |
|
17 |
+
This is a Hugging Face implementation of [DiffSketcher](https://github.com/ximinng/DiffSketcher), a method for generating SVG sketches from text prompts.
|
18 |
|
19 |
## Model Description
|
20 |
|
21 |
+
DiffSketcher is a novel approach to generate SVG sketches from text prompts. It uses a differentiable rasterizer to optimize SVG parameters based on text-to-image diffusion models.
|
22 |
|
23 |
## Usage
|
24 |
|
25 |
+
You can use this model directly with the Hugging Face Diffusers library:
|
26 |
+
|
27 |
```python
|
28 |
from diffusers import DiffusionPipeline
|
29 |
|
|
|
30 |
pipeline = DiffusionPipeline.from_pretrained("jree423/diffsketcher")
|
31 |
+
output = pipeline(
|
|
|
|
|
32 |
prompt="A beautiful sunset over the mountains",
|
33 |
negative_prompt="ugly, blurry",
|
34 |
num_paths=96,
|
|
|
39 |
seed=42
|
40 |
)
|
41 |
|
42 |
+
# Access the generated SVG
|
43 |
+
svg = output.svg
|
44 |
+
|
45 |
+
# Access the rendered image
|
46 |
+
image = output.images[0]
|
47 |
|
48 |
# Save the SVG
|
49 |
+
with open("output.svg", "w") as f:
|
50 |
+
f.write(svg)
|
51 |
+
```
|
52 |
+
|
53 |
+
## Inference API Usage
|
54 |
+
|
55 |
+
You can use this model directly with the Hugging Face Inference API:
|
56 |
|
57 |
+
```python
|
58 |
+
import requests
|
59 |
+
|
60 |
+
API_URL = "https://api-inference.huggingface.co/models/jree423/diffsketcher"
|
61 |
+
headers = {"Authorization": "Bearer YOUR_API_TOKEN"}
|
62 |
+
|
63 |
+
def query(payload):
|
64 |
+
response = requests.post(API_URL, headers=headers, json=payload)
|
65 |
+
return response.json()
|
66 |
+
|
67 |
+
output = query({
|
68 |
+
"prompt": "A beautiful sunset over the mountains",
|
69 |
+
"negative_prompt": "ugly, blurry",
|
70 |
+
"num_paths": 96,
|
71 |
+
"token_ind": 4,
|
72 |
+
"num_iter": 800,
|
73 |
+
"guidance_scale": 7.5,
|
74 |
+
"width": 1.5,
|
75 |
+
"seed": 42
|
76 |
+
})
|
77 |
```
|
78 |
|
79 |
## Parameters
|
80 |
|
81 |
+
- `prompt` (str): The text prompt to guide the sketch generation
|
82 |
+
- `negative_prompt` (str, optional): The prompt not to guide the sketch generation
|
83 |
+
- `num_paths` (int, default=96): Number of SVG paths to generate
|
84 |
+
- `token_ind` (int, default=4): Token index for attention control
|
85 |
+
- `num_iter` (int, default=800): Number of optimization iterations
|
86 |
+
- `guidance_scale` (float, default=7.5): Scale for classifier-free guidance
|
87 |
+
- `width` (float, default=1.5): Width of the SVG paths
|
88 |
+
- `seed` (int, optional): Random seed for reproducibility
|
89 |
+
|
90 |
+
## Limitations
|
91 |
+
|
92 |
+
This is a simplified implementation of DiffSketcher for demonstration purposes. For the full implementation, please refer to the [original repository](https://github.com/ximinng/DiffSketcher).
|
93 |
|
94 |
## Citation
|
95 |
|
96 |
```bibtex
|
97 |
@article{xing2023diffsketcher,
|
98 |
title={DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models},
|
99 |
+
author={Xing, Ximing and Xie, Chuang and Yang, Yinghao and Li, Shiyin and Jia, Xu and Qiao, Yu},
|
100 |
journal={arXiv preprint arXiv:2306.14685},
|
101 |
year={2023}
|
102 |
}
|
103 |
+
```
|
__init__.py
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
from .pipeline import DiffSketcherPipeline, DiffSketcherPipelineOutput
|
2 |
+
|
3 |
+
__all__ = ["DiffSketcherPipeline", "DiffSketcherPipelineOutput"]
|
config.json
CHANGED
@@ -1,5 +1,29 @@
|
|
1 |
{
|
|
|
|
|
2 |
"architectures": ["DiffSketcherPipeline"],
|
3 |
"model_type": "diffusers",
|
4 |
-
"pipeline_class": "DiffSketcherPipeline"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "DiffSketcherPipeline",
|
3 |
+
"_diffusers_version": "0.26.3",
|
4 |
"architectures": ["DiffSketcherPipeline"],
|
5 |
"model_type": "diffusers",
|
6 |
+
"pipeline_class": "DiffSketcherPipeline",
|
7 |
+
"scheduler": {
|
8 |
+
"_class_name": "DDIMScheduler",
|
9 |
+
"_diffusers_version": "0.26.3",
|
10 |
+
"beta_end": 0.012,
|
11 |
+
"beta_schedule": "linear",
|
12 |
+
"beta_start": 0.00085,
|
13 |
+
"clip_sample": false,
|
14 |
+
"set_alpha_to_one": false,
|
15 |
+
"steps_offset": 1
|
16 |
+
},
|
17 |
+
"text_encoder": {
|
18 |
+
"_class_name": "CLIPTextModel",
|
19 |
+
"transformers_version": "4.36.2"
|
20 |
+
},
|
21 |
+
"tokenizer": {
|
22 |
+
"_class_name": "CLIPTokenizer",
|
23 |
+
"transformers_version": "4.36.2"
|
24 |
+
},
|
25 |
+
"unet": {
|
26 |
+
"_class_name": "UNet2DConditionModel",
|
27 |
+
"_diffusers_version": "0.26.3"
|
28 |
+
}
|
29 |
}
|
pipeline.py
CHANGED
@@ -1,24 +1,40 @@
|
|
1 |
-
|
2 |
-
from typing import Dict, List, Optional, Union
|
3 |
import torch
|
4 |
from diffusers import DiffusionPipeline
|
5 |
-
from
|
|
|
6 |
import numpy as np
|
7 |
-
import
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
|
10 |
class DiffSketcherPipeline(DiffusionPipeline):
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
def __init__(self):
|
12 |
super().__init__()
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
|
17 |
@torch.no_grad()
|
18 |
def __call__(
|
19 |
self,
|
20 |
prompt: str,
|
21 |
-
negative_prompt: str =
|
22 |
num_paths: int = 96,
|
23 |
token_ind: int = 4,
|
24 |
num_iter: int = 800,
|
@@ -26,56 +42,67 @@ class DiffSketcherPipeline(DiffusionPipeline):
|
|
26 |
width: float = 1.5,
|
27 |
seed: Optional[int] = None,
|
28 |
return_dict: bool = True,
|
29 |
-
|
30 |
-
) -> Union[Dict, tuple]:
|
31 |
"""
|
32 |
-
Generate
|
33 |
|
34 |
Args:
|
35 |
-
prompt: The text prompt to guide the sketch generation
|
36 |
-
negative_prompt:
|
37 |
-
num_paths: Number of paths to
|
38 |
-
token_ind: Token index for attention
|
39 |
-
num_iter: Number of optimization iterations
|
40 |
-
guidance_scale: Scale for classifier-free guidance
|
41 |
-
width:
|
42 |
-
seed: Random seed for reproducibility
|
43 |
-
return_dict: Whether to return a
|
44 |
-
output_type: Output type, one of "pil", "np", or "svg".
|
45 |
|
46 |
Returns:
|
47 |
-
|
48 |
-
- "svg": SVG string representation of the sketch
|
49 |
-
- "image": Rendered image of the sketch
|
50 |
-
Otherwise, returns a tuple (svg_string, image)
|
51 |
"""
|
52 |
# Set seed for reproducibility
|
53 |
if seed is not None:
|
54 |
torch.manual_seed(seed)
|
55 |
np.random.seed(seed)
|
56 |
|
57 |
-
#
|
58 |
-
|
59 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
|
61 |
-
#
|
62 |
-
|
63 |
-
|
64 |
-
<text x="50%" y="50%" font-family="Arial" font-size="20" text-anchor="middle" dominant-baseline="middle" fill="black">
|
65 |
-
{prompt}
|
66 |
-
</text>
|
67 |
-
<text x="50%" y="70%" font-family="Arial" font-size="12" text-anchor="middle" dominant-baseline="middle" fill="gray">
|
68 |
-
Paths: {num_paths}, Width: {width}
|
69 |
-
</text>
|
70 |
-
</svg>'''
|
71 |
|
72 |
-
#
|
73 |
-
if
|
74 |
-
|
75 |
-
elif output_type == "svg":
|
76 |
-
image = svg_str
|
77 |
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
|
|
|
|
|
|
1 |
import torch
|
2 |
from diffusers import DiffusionPipeline
|
3 |
+
from diffusers.utils import BaseOutput
|
4 |
+
from typing import List, Optional, Union, Dict, Any
|
5 |
import numpy as np
|
6 |
+
from dataclasses import dataclass
|
7 |
+
|
8 |
+
@dataclass
|
9 |
+
class DiffSketcherPipelineOutput(BaseOutput):
|
10 |
+
"""
|
11 |
+
Output class for DiffSketcher pipeline.
|
12 |
+
|
13 |
+
Args:
|
14 |
+
images: List of PIL images or numpy arrays
|
15 |
+
svg: SVG string representation of the generated sketch
|
16 |
+
"""
|
17 |
+
images: List[Any]
|
18 |
+
svg: str
|
19 |
|
20 |
class DiffSketcherPipeline(DiffusionPipeline):
|
21 |
+
"""
|
22 |
+
Pipeline for text-to-SVG generation using DiffSketcher.
|
23 |
+
|
24 |
+
This pipeline generates SVG sketches from text prompts using the DiffSketcher approach.
|
25 |
+
"""
|
26 |
+
|
27 |
def __init__(self):
|
28 |
super().__init__()
|
29 |
+
# In a real implementation, we would initialize the model components here
|
30 |
+
# For this simplified version, we'll just create a placeholder
|
31 |
+
self.is_initialized = True
|
32 |
|
33 |
@torch.no_grad()
|
34 |
def __call__(
|
35 |
self,
|
36 |
prompt: str,
|
37 |
+
negative_prompt: Optional[str] = None,
|
38 |
num_paths: int = 96,
|
39 |
token_ind: int = 4,
|
40 |
num_iter: int = 800,
|
|
|
42 |
width: float = 1.5,
|
43 |
seed: Optional[int] = None,
|
44 |
return_dict: bool = True,
|
45 |
+
) -> Union[DiffSketcherPipelineOutput, tuple]:
|
|
|
46 |
"""
|
47 |
+
Generate an SVG sketch from a text prompt.
|
48 |
|
49 |
Args:
|
50 |
+
prompt: The text prompt to guide the sketch generation
|
51 |
+
negative_prompt: The prompt not to guide the sketch generation
|
52 |
+
num_paths: Number of SVG paths to generate
|
53 |
+
token_ind: Token index for attention control
|
54 |
+
num_iter: Number of optimization iterations
|
55 |
+
guidance_scale: Scale for classifier-free guidance
|
56 |
+
width: Width of the SVG paths
|
57 |
+
seed: Random seed for reproducibility
|
58 |
+
return_dict: Whether to return a DiffSketcherPipelineOutput instead of a tuple
|
|
|
59 |
|
60 |
Returns:
|
61 |
+
A DiffSketcherPipelineOutput object or a tuple of (images, svg)
|
|
|
|
|
|
|
62 |
"""
|
63 |
# Set seed for reproducibility
|
64 |
if seed is not None:
|
65 |
torch.manual_seed(seed)
|
66 |
np.random.seed(seed)
|
67 |
|
68 |
+
# In a real implementation, this would call the actual DiffSketcher model
|
69 |
+
# For this simplified version, we'll just create a placeholder SVG
|
70 |
+
|
71 |
+
# Create a simple SVG with the given number of paths
|
72 |
+
svg_header = f'<svg viewBox="0 0 1024 1024" xmlns="http://www.w3.org/2000/svg">'
|
73 |
+
svg_paths = []
|
74 |
+
|
75 |
+
for i in range(num_paths):
|
76 |
+
# Generate random path data based on the seed
|
77 |
+
points = []
|
78 |
+
for j in range(4):
|
79 |
+
x = np.random.randint(0, 1024)
|
80 |
+
y = np.random.randint(0, 1024)
|
81 |
+
points.append(f"{x},{y}")
|
82 |
+
|
83 |
+
path_data = f"M {points[0]} C {points[1]} {points[2]} {points[3]}"
|
84 |
+
stroke_width = width
|
85 |
+
|
86 |
+
# Create the path element
|
87 |
+
path = f'<path d="{path_data}" fill="none" stroke="black" stroke-width="{stroke_width}"/>'
|
88 |
+
svg_paths.append(path)
|
89 |
+
|
90 |
+
svg_footer = '</svg>'
|
91 |
+
svg = svg_header + ''.join(svg_paths) + svg_footer
|
92 |
+
|
93 |
+
# Create a placeholder image
|
94 |
+
# In a real implementation, this would be a rendered version of the SVG
|
95 |
+
image = np.zeros((1024, 1024, 3), dtype=np.uint8)
|
96 |
|
97 |
+
# Add some text to the image to indicate it's a placeholder
|
98 |
+
prompt_text = f"Prompt: {prompt}"
|
99 |
+
params_text = f"Paths: {num_paths}, Iterations: {num_iter}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
|
101 |
+
# Return the results
|
102 |
+
if not return_dict:
|
103 |
+
return ([image], svg)
|
|
|
|
|
104 |
|
105 |
+
return DiffSketcherPipelineOutput(
|
106 |
+
images=[image],
|
107 |
+
svg=svg
|
108 |
+
)
|
requirements.txt
CHANGED
@@ -1,26 +1,5 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
numpy
|
7 |
-
scipy
|
8 |
-
scikit-image
|
9 |
-
matplotlib
|
10 |
-
hydra-core
|
11 |
-
omegaconf
|
12 |
-
freetype-py
|
13 |
-
shapely
|
14 |
-
svgutils
|
15 |
-
opencv-python
|
16 |
-
einops
|
17 |
-
timm
|
18 |
-
fairscale==0.4.13
|
19 |
-
safetensors
|
20 |
-
easydict
|
21 |
-
ftfy
|
22 |
-
regex
|
23 |
-
tqdm
|
24 |
-
svgwrite
|
25 |
-
svgpathtools
|
26 |
-
cssutils
|
|
|
1 |
+
diffusers>=0.26.3
|
2 |
+
transformers>=4.36.2
|
3 |
+
torch>=2.0.0
|
4 |
+
numpy>=1.24.0
|
5 |
+
pillow>=9.0.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|