github/ControlNet
1
1
Fork 0
mirror of https://github.com/lllyasviel/ControlNet.git synced 2026-04-24 03:00:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

Allow setting -1 as seed for random

Browse Source
This commit is contained in:
scarbain
2023-02-12 19:54:36 +01:00
parent f39054af96
commit 3933672c28
10 changed files with 40 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
gradio_canny2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -32,6 +33,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -75,7 +78,7 @@ with block:
high_threshold = gr.Slider(label="Canny high threshold", minimum=1, maximum=255, value=200, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_depth2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -34,6 +35,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -76,7 +79,7 @@ with block:
detect_resolution = gr.Slider(label="Depth Resolution", minimum=128, maximum=1024, value=384, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_fake_scribble2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -38,6 +39,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -80,7 +83,7 @@ with block:
detect_resolution = gr.Slider(label="HED Resolution", minimum=128, maximum=1024, value=512, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_hed2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -34,6 +35,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -76,7 +79,7 @@ with block:
detect_resolution = gr.Slider(label="HED Resolution", minimum=128, maximum=1024, value=512, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_hough2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -34,6 +35,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -78,7 +81,7 @@ with block:
distance_threshold = gr.Slider(label="Hough distance threshold (MLSD)", minimum=0.01, maximum=20.0, value=0.1, step=0.01)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_normal2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -34,6 +35,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -77,7 +80,7 @@ with block:
bg_threshold = gr.Slider(label="Normal background threshold", minimum=0.0, maximum=1.0, value=0.4, step=0.01)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

6
gradio_pose2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -13,7 +14,6 @@ from annotator.openpose import apply_openpose
from cldm.model import create_model, load_state_dict
from ldm.models.diffusion.ddim import DDIMSampler
model = create_model('./models/cldm_v15.yaml').cpu()
model.load_state_dict(load_state_dict('./models/control_sd15_openpose.pth', location='cpu'))
model = model.cuda()
@@ -34,6 +34,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -76,7 +78,7 @@ with block:
detect_resolution = gr.Slider(label="OpenPose Resolution", minimum=128, maximum=1024, value=512, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_scribble2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -31,6 +32,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -72,7 +75,7 @@ with block:
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_scribble2image_interactive.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -31,6 +32,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -82,7 +85,7 @@ with block:
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",

5
gradio_seg2image.py
View File

@@ -6,6 +6,7 @@ import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
@@ -33,6 +34,8 @@ def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resoluti
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 2147483647)
seed_everything(seed)
if config.save_memory:
@@ -75,7 +78,7 @@ with block:
detect_resolution = gr.Slider(label="Segmentation Resolution", minimum=128, maximum=1024, value=512, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
eta = gr.Number(label="eta (DDIM)", value=0.0)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",