dvir-bria commited on
Commit
67cf87b
1 Parent(s): df77a45

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md CHANGED
@@ -2,4 +2,86 @@
2
  license: other
3
  license_name: bria-2.3
4
  license_link: https://bria.ai/customer-general-terms-and-conditions
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: other
3
  license_name: bria-2.3
4
  license_link: https://bria.ai/customer-general-terms-and-conditions
5
+ inference: false
6
+
7
+ tags:
8
+ - text-to-image
9
+ - controlnet model
10
+ - legal liability
11
+ - commercial use
12
+ extra_gated_prompt: This model weights by BRIA AI can be obtained after a commercial license is agreed upon. Fill in the form below and we reach out to you.
13
+ extra_gated_fields:
14
+ Name: text
15
+ Company/Org name: text
16
+ Org Type (Early/Growth Startup, Enterprise, Academy): text
17
+ Role: text
18
+ Country: text
19
+ Email: text
20
+ By submitting this form, I agree to BRIA’s Privacy policy and Terms & conditions, see links below: checkbox
21
  ---
22
+
23
+ # BRIA 2.3 ControlNet Canny Model Card
24
+
25
+
26
+ BRIA 2.3 ControlNet-Canny, trained on the foundation of [BRIA 2.3 Text-to-Image](https://huggingface.co/briaai/BRIA-2.3), enables the generation of high-quality images guided by a textual prompt and the extracted edge map from an input image. This allows for the creation of different variations of an image, all sharing the same geometry.
27
+
28
+
29
+ [BRIA 2.3](https://huggingface.co/briaai/BRIA-2.3) was trained from scratch exclusively on licensed data from our esteemed data partners. Therefore, they are safe for commercial use and provide full legal liability coverage for copyright and privacy infringement, as well as harmful content mitigation. That is, our dataset does not contain copyrighted materials, such as fictional characters, logos, trademarks, public figures, harmful content, or privacy-infringing content.
30
+
31
+ ![photo-4426232_collage.png](https://cdn-uploads.huggingface.co/production/uploads/6571c468b622b6c62c1ac4da/VzUtWzN0KdT7B-xoBNEcB.png)
32
+
33
+
34
+ ### Model Description
35
+
36
+ - **Developed by:** BRIA AI
37
+ - **Model type:** [ControlNet](https://huggingface.co/docs/diffusers/using-diffusers/controlnet) for Latent diffusion
38
+ - **License:** [bria-2.3](https://bria.ai/bria-huggingface-model-license-agreement/)
39
+
40
+ - **Model Description:** ControlNet Canny for BRIA 2.3 Text-to-Image model. The model generates images guided by text and the edge map of the conditioned image.
41
+ - **Resources for more information:** [BRIA AI](https://bria.ai/)
42
+
43
+
44
+ ### Get Access
45
+ BRIA 2.3 ControlNet-Canny requires access to BRIA 2.3 Text-to-Image. For more information, [click here](https://huggingface.co/briaai/BRIA-2.3).
46
+
47
+
48
+
49
+
50
+
51
+
52
+ ### Code example using Diffusers
53
+
54
+
55
+ ```
56
+ pip install diffusers
57
+ ```
58
+
59
+
60
+ ```py
61
+ from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
62
+ import torch
63
+
64
+ controlnet = ControlNetModel.from_pretrained(
65
+ "briaai/BRIA-2.3-ControlNet-Canny",
66
+ torch_dtype=torch.float16
67
+ )
68
+
69
+ pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
70
+ "briaai/BRIA-2.3",
71
+ controlnet=controlnet,
72
+ torch_dtype=torch.float16,
73
+ )
74
+ pipe.to("cuda")
75
+
76
+ prompt = "A portrait of a Beautiful and playful ethereal singer, golden designs, highly detailed, blurry background"
77
+ negative_prompt = "Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"
78
+
79
+ # Calculate Canny image
80
+ input_image = cv2.imread('pics/singer.png')
81
+ input_image = cv2.Canny(input_image, low_threshold, high_threshold)
82
+ input_image = input_image[:, :, None]
83
+ input_image = np.concatenate([input_image, input_image, input_image], axis=2)
84
+ canny_image = Image.fromarray(image)
85
+
86
+ image = pipe(prompt=prompt, negative_prompt=negative_prompt, image=canny_image, controlnet_conditioning_scale=1.0, height=1024, width=1024).images[0]
87
+ ```