comi-logic/Wan2GP
7
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Vace improvements

Browse Source
This commit is contained in:
DeepBeepMeep
2025-05-23 21:51:00 +02:00
parent 6706709230
commit 86725a65d4
8 changed files with 631 additions and 343 deletions
Download Patch File Download Diff File Expand all files Collapse all files

633
preprocessing/matanyone/app.py
View File

@@ -85,7 +85,7 @@ def get_frames_from_image(image_input, image_state):
model.samcontroler.sam_controler.reset_image()
model.samcontroler.sam_controler.set_image(image_state["origin_images"][0])
return image_state, image_info, image_state["origin_images"][0], \
gr.update(visible=True, maximum=10, value=10), gr.update(visible=True, maximum=len(frames), value=len(frames)), gr.update(visible=False, maximum=len(frames), value=len(frames)), \
gr.update(visible=True, maximum=10, value=10), gr.update(visible=False, maximum=len(frames), value=len(frames)), \
gr.update(visible=True), gr.update(visible=True), \
gr.update(visible=True), gr.update(visible=True),\
gr.update(visible=True), gr.update(visible=True), \
@@ -273,6 +273,57 @@ def save_video(frames, output_path, fps):
return output_path
# image matting
def image_matting(video_state, interactive_state, mask_dropdown, erode_kernel_size, dilate_kernel_size, refine_iter):
matanyone_processor = InferenceCore(matanyone_model, cfg=matanyone_model.cfg)
if interactive_state["track_end_number"]:
following_frames = video_state["origin_images"][video_state["select_frame_number"]:interactive_state["track_end_number"]]
else:
following_frames = video_state["origin_images"][video_state["select_frame_number"]:]
if interactive_state["multi_mask"]["masks"]:
if len(mask_dropdown) == 0:
mask_dropdown = ["mask_001"]
mask_dropdown.sort()
template_mask = interactive_state["multi_mask"]["masks"][int(mask_dropdown[0].split("_")[1]) - 1] * (int(mask_dropdown[0].split("_")[1]))
for i in range(1,len(mask_dropdown)):
mask_number = int(mask_dropdown[i].split("_")[1]) - 1
template_mask = np.clip(template_mask+interactive_state["multi_mask"]["masks"][mask_number]*(mask_number+1), 0, mask_number+1)
video_state["masks"][video_state["select_frame_number"]]= template_mask
else:
template_mask = video_state["masks"][video_state["select_frame_number"]]
# operation error
if len(np.unique(template_mask))==1:
template_mask[0][0]=1
foreground, alpha = matanyone(matanyone_processor, following_frames, template_mask*255, r_erode=erode_kernel_size, r_dilate=dilate_kernel_size, n_warmup=refine_iter)
foreground_mat = False
output_frames = []
for frame_origin, frame_alpha in zip(following_frames, alpha):
if foreground_mat:
frame_alpha[frame_alpha > 127] = 255
frame_alpha[frame_alpha <= 127] = 0
else:
frame_temp = frame_alpha.copy()
frame_alpha[frame_temp > 127] = 0
frame_alpha[frame_temp <= 127] = 255
output_frame = np.bitwise_and(frame_origin, 255-frame_alpha)
frame_grey = frame_alpha.copy()
frame_grey[frame_alpha == 255] = 255
output_frame += frame_grey
output_frames.append(output_frame)
foreground = output_frames
foreground_output = Image.fromarray(foreground[-1])
alpha_output = Image.fromarray(alpha[-1][:,:,0])
return foreground_output, gr.update(visible=True)
# video matting
def video_matting(video_state, end_slider, matting_type, interactive_state, mask_dropdown, erode_kernel_size, dilate_kernel_size):
matanyone_processor = InferenceCore(matanyone_model, cfg=matanyone_model.cfg)
@@ -397,7 +448,7 @@ def restart():
"inference_times": 0,
"negative_click_times" : 0,
"positive_click_times": 0,
"mask_save": arg_mask_save,
"mask_save": False,
"multi_mask": {
"mask_names": [],
"masks": []
@@ -457,6 +508,15 @@ def export_to_vace_video_input(foreground_video_output):
gr.Info("Masked Video Input transferred to Vace For Inpainting")
return "V#" + str(time.time()), foreground_video_output
def export_image(image_refs, image_output):
gr.Info("Masked Image transferred to Current Video")
# return "MV#" + str(time.time()), foreground_video_output, alpha_video_output
if image_refs == None:
image_refs =[]
image_refs.append( image_output)
return image_refs
def export_to_current_video_engine(foreground_video_output, alpha_video_output):
gr.Info("Masked Video Input and Full Mask transferred to Current Video Engine For Inpainting")
# return "MV#" + str(time.time()), foreground_video_output, alpha_video_output
@@ -471,15 +531,18 @@ def teleport_to_vace_1_3B():
def teleport_to_vace_14B():
return gr.Tabs(selected="video_gen"), gr.Dropdown(value="vace_14B")
def display(tabs, model_choice, vace_video_input, vace_video_mask, video_prompt_video_guide_trigger):
def display(tabs, model_choice, vace_video_input, vace_video_mask, vace_image_refs, video_prompt_video_guide_trigger):
# my_tab.select(fn=load_unload_models, inputs=[], outputs=[])
media_url = "https://github.com/pq-yang/MatAnyone/releases/download/media/"
# download assets
gr.Markdown("Mast Edition is provided by MatAnyone")
gr.Markdown("<B>Mast Edition is provided by MatAnyone</B>")
gr.Markdown("If you have some trouble creating the perfect mask, be aware of these tips:")
gr.Markdown("- Using the Matanyone Settings you can also define Negative Point Prompts to remove parts of the current selection.")
gr.Markdown("- Sometime it is very hard to fit everything you want in a single mask, it may be much easier to combine multiple independent sub Masks before producing the Matting : each sub Mask is created by selecting an area of an image and by clicking the Add Mask button. Sub masks can then be enabled / disabled in the Matanyone settings.")
with gr.Column( visible=True):
with gr.Row():
with gr.Accordion("Video Tutorial (click to expand)", open=False, elem_classes="custom-bg"):
@@ -493,216 +556,368 @@ def display(tabs, model_choice, vace_video_input, vace_video_mask, video_prompt_
gr.Video(value="preprocessing/matanyone/tutorial_multi_targets.mp4", elem_classes="video")
click_state = gr.State([[],[]])
interactive_state = gr.State({
"inference_times": 0,
"negative_click_times" : 0,
"positive_click_times": 0,
"mask_save": arg_mask_save,
"multi_mask": {
"mask_names": [],
"masks": []
},
"track_end_number": None,
}
)
video_state = gr.State(
{
"user_name": "",
"video_name": "",
"origin_images": None,
"painted_images": None,
"masks": None,
"inpaint_masks": None,
"logits": None,
"select_frame_number": 0,
"fps": 16,
"audio": "",
}
)
with gr.Column( visible=True):
with gr.Row():
with gr.Accordion('MatAnyone Settings (click to expand)', open=False):
with gr.Row():
erode_kernel_size = gr.Slider(label='Erode Kernel Size',
minimum=0,
maximum=30,
step=1,
value=10,
info="Erosion on the added mask",
interactive=True)
dilate_kernel_size = gr.Slider(label='Dilate Kernel Size',
minimum=0,
maximum=30,
step=1,
value=10,
info="Dilation on the added mask",
interactive=True)
with gr.Row():
image_selection_slider = gr.Slider(minimum=1, maximum=100, step=1, value=1, label="Start Frame", info="Choose the start frame for target assignment and video matting", visible=False)
end_selection_slider = gr.Slider(minimum=1, maximum=300, step=1, value=81, label="Last Frame to Process", info="Last Frame to Process", visible=False)
track_pause_number_slider = gr.Slider(minimum=1, maximum=100, step=1, value=1, label="End frame", visible=False)
with gr.Row():
point_prompt = gr.Radio(
choices=["Positive", "Negative"],
value="Positive",
label="Point Prompt",
info="Click to add positive or negative point for target mask",
interactive=True,
visible=False,
min_width=100,
scale=1)
matting_type = gr.Radio(
choices=["Foreground", "Background"],
value="Foreground",
label="Matting Type",
info="Type of Video Matting to Generate",
interactive=True,
visible=False,
min_width=100,
scale=1)
mask_dropdown = gr.Dropdown(multiselect=True, value=[], label="Mask Selection", info="Choose 1~all mask(s) added in Step 2", visible=False, scale=2)
gr.Markdown("---")
with gr.Column():
# input video
with gr.Row(equal_height=True):
with gr.Column(scale=2):
gr.Markdown("## Step1: Upload video")
with gr.Column(scale=2):
step2_title = gr.Markdown("## Step2: Add masks <small>(Several clicks then **`Add Mask`** <u>one by one</u>)</small>", visible=False)
with gr.Row(equal_height=True):
with gr.Column(scale=2):
video_input = gr.Video(label="Input Video", elem_classes="video")
extract_frames_button = gr.Button(value="Load Video", interactive=True, elem_classes="new_button")
with gr.Column(scale=2):
video_info = gr.Textbox(label="Video Info", visible=False)
template_frame = gr.Image(label="Start Frame", type="pil",interactive=True, elem_id="template_frame", visible=False, elem_classes="image")
with gr.Row():
clear_button_click = gr.Button(value="Clear Clicks", interactive=True, visible=False, min_width=100)
add_mask_button = gr.Button(value="Set Mask", interactive=True, visible=False, min_width=100)
remove_mask_button = gr.Button(value="Remove Mask", interactive=True, visible=False, min_width=100) # no use
matting_button = gr.Button(value="Generate Video Matting", interactive=True, visible=False, min_width=100)
with gr.Row():
gr.Markdown("")
with gr.Tabs():
with gr.TabItem("Video"):
# output video
with gr.Column() as output_row: #equal_height=True
with gr.Row():
with gr.Column(scale=2):
foreground_video_output = gr.Video(label="Masked Video Output", visible=False, elem_classes="video")
foreground_output_button = gr.Button(value="Black & White Video Output", visible=False, elem_classes="new_button")
with gr.Column(scale=2):
alpha_video_output = gr.Video(label="B & W Mask Video Output", visible=False, elem_classes="video")
click_state = gr.State([[],[]])
interactive_state = gr.State({
"inference_times": 0,
"negative_click_times" : 0,
"positive_click_times": 0,
"mask_save": arg_mask_save,
"multi_mask": {
"mask_names": [],
"masks": []
},
"track_end_number": None,
}
)
video_state = gr.State(
{
"user_name": "",
"video_name": "",
"origin_images": None,
"painted_images": None,
"masks": None,
"inpaint_masks": None,
"logits": None,
"select_frame_number": 0,
"fps": 16,
"audio": "",
}
)
with gr.Column( visible=True):
with gr.Row():
with gr.Accordion('MatAnyone Settings (click to expand)', open=False):
with gr.Row():
erode_kernel_size = gr.Slider(label='Erode Kernel Size',
minimum=0,
maximum=30,
step=1,
value=10,
info="Erosion on the added mask",
interactive=True)
dilate_kernel_size = gr.Slider(label='Dilate Kernel Size',
minimum=0,
maximum=30,
step=1,
value=10,
info="Dilation on the added mask",
interactive=True)
with gr.Row():
image_selection_slider = gr.Slider(minimum=1, maximum=100, step=1, value=1, label="Start Frame", info="Choose the start frame for target assignment and video matting", visible=False)
end_selection_slider = gr.Slider(minimum=1, maximum=300, step=1, value=81, label="Last Frame to Process", info="Last Frame to Process", visible=False)
track_pause_number_slider = gr.Slider(minimum=1, maximum=100, step=1, value=1, label="End frame", visible=False)
with gr.Row():
point_prompt = gr.Radio(
choices=["Positive", "Negative"],
value="Positive",
label="Point Prompt",
info="Click to add positive or negative point for target mask",
interactive=True,
visible=False,
min_width=100,
scale=1)
matting_type = gr.Radio(
choices=["Foreground", "Background"],
value="Foreground",
label="Matting Type",
info="Type of Video Matting to Generate",
interactive=True,
visible=False,
min_width=100,
scale=1)
mask_dropdown = gr.Dropdown(multiselect=True, value=[], label="Mask Selection", info="Choose 1~all mask(s) added in Step 2", visible=False, scale=2)
# input video
with gr.Row(equal_height=True):
with gr.Column(scale=2):
gr.Markdown("## Step1: Upload video")
with gr.Column(scale=2):
step2_title = gr.Markdown("## Step2: Add masks <small>(Several clicks then **`Add Mask`** <u>one by one</u>)</small>", visible=False)
with gr.Row(equal_height=True):
with gr.Column(scale=2):
video_input = gr.Video(label="Input Video", elem_classes="video")
extract_frames_button = gr.Button(value="Load Video", interactive=True, elem_classes="new_button")
with gr.Column(scale=2):
video_info = gr.Textbox(label="Video Info", visible=False)
template_frame = gr.Image(label="Start Frame", type="pil",interactive=True, elem_id="template_frame", visible=False, elem_classes="image")
with gr.Row():
clear_button_click = gr.Button(value="Clear Clicks", interactive=True, visible=False, min_width=100)
add_mask_button = gr.Button(value="Set Mask", interactive=True, visible=False, min_width=100)
remove_mask_button = gr.Button(value="Remove Mask", interactive=True, visible=False, min_width=100) # no use
matting_button = gr.Button(value="Generate Video Matting", interactive=True, visible=False, min_width=100)
with gr.Row():
gr.Markdown("")
# output video
with gr.Column() as output_row: #equal_height=True
with gr.Row():
with gr.Column(scale=2):
foreground_video_output = gr.Video(label="Masked Video Output", visible=False, elem_classes="video")
foreground_output_button = gr.Button(value="Black & White Video Output", visible=False, elem_classes="new_button")
with gr.Column(scale=2):
alpha_video_output = gr.Video(label="B & W Mask Video Output", visible=False, elem_classes="video")
alpha_output_button = gr.Button(value="Alpha Mask Output", visible=False, elem_classes="new_button")
with gr.Row():
with gr.Row(visible= False):
export_to_vace_video_14B_btn = gr.Button("Export to current Video Input Video For Inpainting", visible= False)
with gr.Row(visible= True):
export_to_current_video_engine_btn = gr.Button("Export to current Video Input and Video Mask", visible= False)
export_to_vace_video_14B_btn.click( fn=teleport_to_vace_14B, inputs=[], outputs=[tabs, model_choice]).then(
fn=export_to_current_video_engine, inputs= [foreground_video_output, alpha_video_output], outputs= [video_prompt_video_guide_trigger, vace_video_input, vace_video_mask])
export_to_current_video_engine_btn.click( fn=export_to_current_video_engine, inputs= [foreground_video_output, alpha_video_output], outputs= [vace_video_input, vace_video_mask]).then( #video_prompt_video_guide_trigger,
fn=teleport_to_video_tab, inputs= [], outputs= [tabs])
# first step: get the video information
extract_frames_button.click(
fn=get_frames_from_video,
inputs=[
video_input, video_state
],
outputs=[video_state, video_info, template_frame,
image_selection_slider, end_selection_slider, track_pause_number_slider, point_prompt, matting_type, clear_button_click, add_mask_button, matting_button, template_frame,
foreground_video_output, alpha_video_output, foreground_output_button, alpha_output_button, mask_dropdown, step2_title]
)
# second step: select images from slider
image_selection_slider.release(fn=select_video_template,
inputs=[image_selection_slider, video_state, interactive_state],
outputs=[template_frame, video_state, interactive_state], api_name="select_image")
track_pause_number_slider.release(fn=get_end_number,
inputs=[track_pause_number_slider, video_state, interactive_state],
outputs=[template_frame, interactive_state], api_name="end_image")
# click select image to get mask using sam
template_frame.select(
fn=sam_refine,
inputs=[video_state, point_prompt, click_state, interactive_state],
outputs=[template_frame, video_state, interactive_state]
)
# add different mask
add_mask_button.click(
fn=add_multi_mask,
inputs=[video_state, interactive_state, mask_dropdown],
outputs=[interactive_state, mask_dropdown, template_frame, click_state]
)
remove_mask_button.click(
fn=remove_multi_mask,
inputs=[interactive_state, mask_dropdown],
outputs=[interactive_state, mask_dropdown]
)
# video matting
matting_button.click(
fn=show_outputs,
inputs=[],
outputs=[foreground_video_output, alpha_video_output]).then(
fn=video_matting,
inputs=[video_state, end_selection_slider, matting_type, interactive_state, mask_dropdown, erode_kernel_size, dilate_kernel_size],
outputs=[foreground_video_output, alpha_video_output,foreground_video_output, alpha_video_output, export_to_vace_video_14B_btn, export_to_current_video_engine_btn]
)
# click to get mask
mask_dropdown.change(
fn=show_mask,
inputs=[video_state, interactive_state, mask_dropdown],
outputs=[template_frame]
)
# clear input
video_input.change(
fn=restart,
inputs=[],
outputs=[
video_state,
interactive_state,
click_state,
foreground_video_output, alpha_video_output,
template_frame,
image_selection_slider, end_selection_slider, track_pause_number_slider,point_prompt, export_to_vace_video_14B_btn, export_to_current_video_engine_btn, matting_type, clear_button_click,
add_mask_button, matting_button, template_frame, foreground_video_output, alpha_video_output, remove_mask_button, foreground_output_button, alpha_output_button, mask_dropdown, video_info, step2_title
],
queue=False,
show_progress=False)
video_input.clear(
fn=restart,
inputs=[],
outputs=[
video_state,
interactive_state,
click_state,
foreground_video_output, alpha_video_output,
template_frame,
image_selection_slider , end_selection_slider, track_pause_number_slider,point_prompt, export_to_vace_video_14B_btn, export_to_current_video_engine_btn, matting_type, clear_button_click,
add_mask_button, matting_button, template_frame, foreground_video_output, alpha_video_output, remove_mask_button, foreground_output_button, alpha_output_button, mask_dropdown, video_info, step2_title
],
queue=False,
show_progress=False)
# points clear
clear_button_click.click(
fn = clear_click,
inputs = [video_state, click_state,],
outputs = [template_frame,click_state],
)
with gr.TabItem("Image"):
click_state = gr.State([[],[]])
interactive_state = gr.State({
"inference_times": 0,
"negative_click_times" : 0,
"positive_click_times": 0,
"mask_save": False,
"multi_mask": {
"mask_names": [],
"masks": []
},
"track_end_number": None,
}
)
image_state = gr.State(
{
"user_name": "",
"image_name": "",
"origin_images": None,
"painted_images": None,
"masks": None,
"inpaint_masks": None,
"logits": None,
"select_frame_number": 0,
"fps": 30
}
)
with gr.Group(elem_classes="gr-monochrome-group", visible=True):
with gr.Row():
with gr.Accordion('MatAnyone Settings (click to expand)', open=False):
with gr.Row():
erode_kernel_size = gr.Slider(label='Erode Kernel Size',
minimum=0,
maximum=30,
step=1,
value=10,
info="Erosion on the added mask",
interactive=True)
dilate_kernel_size = gr.Slider(label='Dilate Kernel Size',
minimum=0,
maximum=30,
step=1,
value=10,
info="Dilation on the added mask",
interactive=True)
with gr.Row():
image_selection_slider = gr.Slider(minimum=1, maximum=100, step=1, value=1, label="Num of Refinement Iterations", info="More iterations → More details & More time", visible=False)
track_pause_number_slider = gr.Slider(minimum=1, maximum=100, step=1, value=1, label="Track end frame", visible=False)
with gr.Row():
point_prompt = gr.Radio(
choices=["Positive", "Negative"],
value="Positive",
label="Point Prompt",
info="Click to add positive or negative point for target mask",
interactive=True,
visible=False,
min_width=100,
scale=1)
mask_dropdown = gr.Dropdown(multiselect=True, value=[], label="Mask Selection", info="Choose 1~all mask(s) added in Step 2", visible=False)
with gr.Column():
# input image
with gr.Row(equal_height=True):
with gr.Column(scale=2):
gr.Markdown("## Step1: Upload image")
with gr.Column(scale=2):
step2_title = gr.Markdown("## Step2: Add masks <small>(Several clicks then **`Add Mask`** <u>one by one</u>)</small>", visible=False)
with gr.Row(equal_height=True):
with gr.Column(scale=2):
image_input = gr.Image(label="Input Image", elem_classes="image")
extract_frames_button = gr.Button(value="Load Image", interactive=True, elem_classes="new_button")
with gr.Column(scale=2):
image_info = gr.Textbox(label="Image Info", visible=False)
template_frame = gr.Image(type="pil", label="Start Frame", interactive=True, elem_id="template_frame", visible=False, elem_classes="image")
with gr.Row(equal_height=True, elem_classes="mask_button_group"):
clear_button_click = gr.Button(value="Clear Clicks", interactive=True, visible=False, elem_classes="new_button", min_width=100)
add_mask_button = gr.Button(value="Add Mask", interactive=True, visible=False, elem_classes="new_button", min_width=100)
remove_mask_button = gr.Button(value="Remove Mask", interactive=True, visible=False, elem_classes="new_button", min_width=100)
matting_button = gr.Button(value="Image Matting", interactive=True, visible=False, elem_classes="green_button", min_width=100)
# output image
with gr.Row(equal_height=True):
foreground_image_output = gr.Image(type="pil", label="Foreground Output", visible=False, elem_classes="image")
with gr.Row():
with gr.Row():
export_image_btn = gr.Button(value="Add to current Reference Images", visible=False, elem_classes="new_button")
with gr.Column(scale=2, visible= False):
alpha_image_output = gr.Image(type="pil", label="Alpha Output", visible=False, elem_classes="image")
alpha_output_button = gr.Button(value="Alpha Mask Output", visible=False, elem_classes="new_button")
with gr.Row():
with gr.Row(visible= False):
export_to_vace_video_14B_btn = gr.Button("Export to current Video Input Video For Inpainting", visible= False)
with gr.Row(visible= True):
export_to_current_video_engine_btn = gr.Button("Export to current Video Input and Video Mask", visible= False)
export_to_vace_video_14B_btn.click( fn=teleport_to_vace_14B, inputs=[], outputs=[tabs, model_choice]).then(
fn=export_to_current_video_engine, inputs= [foreground_video_output, alpha_video_output], outputs= [video_prompt_video_guide_trigger, vace_video_input, vace_video_mask])
export_to_current_video_engine_btn.click( fn=export_to_current_video_engine, inputs= [foreground_video_output, alpha_video_output], outputs= [vace_video_input, vace_video_mask]).then( #video_prompt_video_guide_trigger,
fn=teleport_to_video_tab, inputs= [], outputs= [tabs])
# first step: get the video information
extract_frames_button.click(
fn=get_frames_from_video,
inputs=[
video_input, video_state
],
outputs=[video_state, video_info, template_frame,
image_selection_slider, end_selection_slider, track_pause_number_slider, point_prompt, matting_type, clear_button_click, add_mask_button, matting_button, template_frame,
foreground_video_output, alpha_video_output, foreground_output_button, alpha_output_button, mask_dropdown, step2_title]
)
# second step: select images from slider
image_selection_slider.release(fn=select_video_template,
inputs=[image_selection_slider, video_state, interactive_state],
outputs=[template_frame, video_state, interactive_state], api_name="select_image")
track_pause_number_slider.release(fn=get_end_number,
inputs=[track_pause_number_slider, video_state, interactive_state],
outputs=[template_frame, interactive_state], api_name="end_image")
# click select image to get mask using sam
template_frame.select(
fn=sam_refine,
inputs=[video_state, point_prompt, click_state, interactive_state],
outputs=[template_frame, video_state, interactive_state]
)
export_image_btn.click( fn=export_image, inputs= [vace_image_refs, foreground_image_output], outputs= [vace_image_refs]).then( #video_prompt_video_guide_trigger,
fn=teleport_to_video_tab, inputs= [], outputs= [tabs])
# add different mask
add_mask_button.click(
fn=add_multi_mask,
inputs=[video_state, interactive_state, mask_dropdown],
outputs=[interactive_state, mask_dropdown, template_frame, click_state]
)
# first step: get the image information
extract_frames_button.click(
fn=get_frames_from_image,
inputs=[
image_input, image_state
],
outputs=[image_state, image_info, template_frame,
image_selection_slider, track_pause_number_slider,point_prompt, clear_button_click, add_mask_button, matting_button, template_frame,
foreground_image_output, alpha_image_output, export_image_btn, alpha_output_button, mask_dropdown, step2_title]
)
# second step: select images from slider
image_selection_slider.release(fn=select_image_template,
inputs=[image_selection_slider, image_state, interactive_state],
outputs=[template_frame, image_state, interactive_state], api_name="select_image")
track_pause_number_slider.release(fn=get_end_number,
inputs=[track_pause_number_slider, image_state, interactive_state],
outputs=[template_frame, interactive_state], api_name="end_image")
# click select image to get mask using sam
template_frame.select(
fn=sam_refine,
inputs=[image_state, point_prompt, click_state, interactive_state],
outputs=[template_frame, image_state, interactive_state]
)
# add different mask
add_mask_button.click(
fn=add_multi_mask,
inputs=[image_state, interactive_state, mask_dropdown],
outputs=[interactive_state, mask_dropdown, template_frame, click_state]
)
remove_mask_button.click(
fn=remove_multi_mask,
inputs=[interactive_state, mask_dropdown],
outputs=[interactive_state, mask_dropdown]
)
# image matting
matting_button.click(
fn=image_matting,
inputs=[image_state, interactive_state, mask_dropdown, erode_kernel_size, dilate_kernel_size, image_selection_slider],
outputs=[foreground_image_output, export_image_btn]
)
remove_mask_button.click(
fn=remove_multi_mask,
inputs=[interactive_state, mask_dropdown],
outputs=[interactive_state, mask_dropdown]
)
# video matting
matting_button.click(
fn=show_outputs,
inputs=[],
outputs=[foreground_video_output, alpha_video_output]).then(
fn=video_matting,
inputs=[video_state, end_selection_slider, matting_type, interactive_state, mask_dropdown, erode_kernel_size, dilate_kernel_size],
outputs=[foreground_video_output, alpha_video_output,foreground_video_output, alpha_video_output, export_to_vace_video_14B_btn, export_to_current_video_engine_btn]
)
# click to get mask
mask_dropdown.change(
fn=show_mask,
inputs=[video_state, interactive_state, mask_dropdown],
outputs=[template_frame]
)
# clear input
video_input.change(
fn=restart,
inputs=[],
outputs=[
video_state,
interactive_state,
click_state,
foreground_video_output, alpha_video_output,
template_frame,
image_selection_slider, end_selection_slider, track_pause_number_slider,point_prompt, export_to_vace_video_14B_btn, export_to_current_video_engine_btn, matting_type, clear_button_click,
add_mask_button, matting_button, template_frame, foreground_video_output, alpha_video_output, remove_mask_button, foreground_output_button, alpha_output_button, mask_dropdown, video_info, step2_title
],
queue=False,
show_progress=False)
video_input.clear(
fn=restart,
inputs=[],
outputs=[
video_state,
interactive_state,
click_state,
foreground_video_output, alpha_video_output,
template_frame,
image_selection_slider , end_selection_slider, track_pause_number_slider,point_prompt, export_to_vace_video_14B_btn, export_to_current_video_engine_btn, matting_type, clear_button_click,
add_mask_button, matting_button, template_frame, foreground_video_output, alpha_video_output, remove_mask_button, foreground_output_button, alpha_output_button, mask_dropdown, video_info, step2_title
],
queue=False,
show_progress=False)
# points clear
clear_button_click.click(
fn = clear_click,
inputs = [video_state, click_state,],
outputs = [template_frame,click_state],
)

BIN
preprocessing/matanyone/tutorial_multi_targets.mp4 Normal file
View File

Binary file not shown.

BIN
preprocessing/matanyone/tutorial_single_target.mp4 Normal file
View File

Binary file not shown.