File size: 5,116 Bytes
9f9752e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
from PIL import Image
import gradio as gr
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
import torch
torch.backends.cuda.matmul.allow_tf32 = True
import gc

controlnet = [ControlNetModel.from_pretrained("ioclab/connow", torch_dtype=torch.float16, use_safetensors=True),ControlNetModel.from_pretrained( "lllyasviel/control_v11p_sd15_seg" , torch_dtype=torch.float16),] 

pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "andite/anything-v4.0",
    controlnet=controlnet,
    torch_dtype=torch.float16,
    safety_checker=None,
)

pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

# pipe.enable_xformers_memory_efficient_attention()
# pipe.enable_model_cpu_offload()
# pipe.enable_attention_slicing()

def infer(
        prompt,
        negative_prompt,
        conditioning_image,
        seg_image,
        num_inference_steps=30,
        size=768,
        guidance_scale=7.0,
        seed=1234,
        ill=0.6,
        seg=1

):

    conditioning_image = Image.fromarray(conditioning_image)
    # conditioning_image = conditioning_image_raw.convert('L')
    seg_image= Image.fromarray(seg_image)
    g_cpu = torch.Generator()

    if seed == -1:
        generator = g_cpu.manual_seed(g_cpu.seed())
    else:
        generator = g_cpu.manual_seed(seed)
    isa = [conditioning_image,seg_image]
    output_image = pipe(
        prompt,
        isa,
        height=size,
        width=size,
        num_inference_steps=num_inference_steps,
        generator=generator,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        controlnet_conditioning_scale=[ill,seg],
        
    ).images[0]

    del conditioning_image, conditioning_image_raw,seg_image
    gc.collect()

    return output_image

with gr.Blocks() as demo:
    gr.Markdown(
        """
    # ControlNet on Brightness

    This is a demo on ControlNet based on brightness.
    """)

    with gr.Row():
        with gr.Column():
            prompt = gr.Textbox(
                label="Prompt",
            )
            negative_prompt = gr.Textbox(
                label="Negative Prompt",
            )
            conditioning_image = gr.Image(
                label="Conditioning Image",
            )
            seg_image = gr.Image(
                label="(Optional)seg Image",
            )
            with gr.Accordion('Advanced options', open=False):
                with gr.Row():
                    num_inference_steps = gr.Slider(
                        10, 40, 20,
                        step=1,
                        label="Steps",
                    )
                    size = gr.Slider(
                        256, 768, 512,
                        step=128,
                        label="Size",
                    )
                with gr.Row():
                    guidance_scale = gr.Slider(
                        label='Guidance Scale',
                        minimum=0.1,
                        maximum=30.0,
                        value=7.0,
                        step=0.1
                    )
                    seed = gr.Slider(
                        label='Seed',
                        value=-1,
                        minimum=-1,
                        maximum=2147483647,
                        step=1,
                        # randomize=True
                    )
                with gr.Row():
                    ill = gr.Slider(
                        label='controlnet_ILL_scale',
                        minimum=0,
                        maximum=1,
                        value=0.6,
                        step=0.05
                    )
                    seg = gr.Slider(
                        label='controlnet_SEG_scale',
                        value=1,
                        minimum=0,
                        maximum=1,
                        step=0.1,
                        # randomize=True
                    )
            submit_btn = gr.Button(
                value="Submit",
                variant="primary"
            )
        with gr.Column(min_width=300):
            output = gr.Image(
                label="Result",
            )

    submit_btn.click(
        fn=infer,
        inputs=[
            prompt, negative_prompt, conditioning_image,seg_image, num_inference_steps, size, guidance_scale, seed,ill,seg
        ],
        outputs=output
    )
    gr.Markdown(
        """
    * [Dataset](https://huggingface.co/datasets/ioclab/grayscale_image_aesthetic_3M) Note that this was handled extra, and a preview version of the processing is here
      [Anime Dataset](https://huggingface.co/datasets/ioclab/lighttestout)  [Nature Dataset] (https://huggingface.co/datasets/ioclab/light)
    * [Diffusers model](https://huggingface.co/ioclab/connow/tree/main), [Web UI model](https://huggingface.co/ioclab/control_v1u_sd15_illumination_webui)
    * [Training Report](https://huggingface.co/ioclab/control_v1u_sd15_illumination_webui), [Doc(Chinese)](https://aigc.ioclab.com/sd-showcase/light_controlnet.html)
    """)

demo.launch()