Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 01:04:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

caption ui redesign

Browse Source 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
This commit is contained in:
Vladimir Mandic
2025-02-15 12:57:19 -05:00
parent af3a5d9866
commit e95bd93f67
12 changed files with 186 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/ui_postprocessing.py
+8 -91
View File
@@ -1,8 +1,6 @@
import json
import gradio as gr
from modules import scripts, shared, ui_common, postprocessing, call_queue, generation_parameters_copypaste
from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call # pylint: disable=unused-import
from modules.interrogate import openclip
def submit_info(image):
@@ -25,81 +23,14 @@ def create_ui():
with gr.Tab('Process Image', id="single_image", elem_id="extras_single_tab") as tab_single:
with gr.Row():
extras_image = gr.Image(label="Source", source="upload", interactive=True, type="pil", elem_id="extras_image")
with gr.Row(elem_id='copy_buttons_process'):
copy_process_buttons = generation_parameters_copypaste.create_buttons(["txt2img", "img2img", "inpaint", "control"])
with gr.Tab('Process Batch', id="batch_process", elem_id="extras_batch_process_tab") as tab_batch:
image_batch = gr.Files(label="Batch process", interactive=True, elem_id="extras_image_batch")
with gr.Tab('Process Folder', id="batch_from_directory", elem_id="extras_batch_directory_tab") as tab_batch_dir:
extras_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, placeholder="A directory on the same machine where the server is running.", elem_id="extras_batch_input_dir")
extras_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, placeholder="Leave blank to save images to the default path.", elem_id="extras_batch_output_dir")
show_extras_results = gr.Checkbox(label='Show result images', value=True, elem_id="extras_show_extras_results")
with gr.Tab("Interrogate Image"):
with gr.Row():
image = gr.Image(type='pil', label="Image")
with gr.Row():
prompt = gr.Textbox(label="Prompt", lines=3)
with gr.Row(elem_id="interrogate_labels"):
medium = gr.Label(elem_id="interrogate_label_medium", label="Medium", num_top_classes=5)
artist = gr.Label(elem_id="interrogate_label_artist", label="Artist", num_top_classes=5)
movement = gr.Label(elem_id="interrogate_label_movement", label="Movement", num_top_classes=5)
trending = gr.Label(elem_id="interrogate_label_trending", label="Trending", num_top_classes=5)
flavor = gr.Label(elem_id="interrogate_label_flavor", label="Flavor", num_top_classes=5)
with gr.Row():
clip_model = gr.Dropdown([], value=shared.opts.interrogate_clip_model, label='CLiP model')
ui_common.create_refresh_button(clip_model, openclip.refresh_clip_models, lambda: {"choices": openclip.refresh_clip_models()}, 'refresh_interrogate_models')
blip_model = gr.Dropdown(list(openclip.caption_models), value=shared.opts.interrogate_blip_model, label='Caption model')
mode = gr.Dropdown(openclip.caption_types, label='Mode', value='fast')
with gr.Accordion(label='Advanced', open=False, visible=True):
with gr.Row():
caption_max_length = gr.Number(label='Max length', value=shared.opts.interrogate_clip_max_length, minimum=16, maximum=512, min_width=300)
chunk_size = gr.Number(label='Chunk size', value=1024, minimum=256, maximum=4096, min_width=300)
min_flavors = gr.Number(label='Min flavors', value=2, minimum=1, maximum=16, min_width=300)
max_flavors = gr.Number(label='Max flavors', value=8, minimum=1, maximum=64, min_width=300)
flavor_intermediate_count = gr.Number(label='Intermediates', value=1024, minimum=256, maximum=4096)
caption_max_length.change(fn=openclip.update_interrogate_params, inputs=[caption_max_length, chunk_size, min_flavors, max_flavors, flavor_intermediate_count], outputs=[])
chunk_size.change(fn=openclip.update_interrogate_params, inputs=[caption_max_length, chunk_size, min_flavors, max_flavors, flavor_intermediate_count], outputs=[])
min_flavors.change(fn=openclip.update_interrogate_params, inputs=[caption_max_length, chunk_size, min_flavors, max_flavors, flavor_intermediate_count], outputs=[])
max_flavors.change(fn=openclip.update_interrogate_params, inputs=[caption_max_length, chunk_size, min_flavors, max_flavors, flavor_intermediate_count], outputs=[])
flavor_intermediate_count.change(fn=openclip.update_interrogate_params, inputs=[caption_max_length, chunk_size, min_flavors, max_flavors, flavor_intermediate_count], outputs=[])
with gr.Row(elem_id='interrogate_buttons_image'):
btn_interrogate_img = gr.Button("Interrogate", elem_id="interrogate_btn_interrogate", variant='primary')
btn_analyze_img = gr.Button("Analyze", elem_id="interrogate_btn_analyze", variant='primary')
btn_unload = gr.Button("Unload", elem_id="interrogate_btn_unload")
with gr.Row(elem_id='copy_buttons_interrogate'):
copy_interrogate_buttons = generation_parameters_copypaste.create_buttons(["txt2img", "img2img", "extras", "control"])
btn_interrogate_img.click(openclip.interrogate_image, inputs=[image, clip_model, blip_model, mode], outputs=prompt)
btn_analyze_img.click(openclip.analyze_image, inputs=[image, clip_model, blip_model], outputs=[medium, artist, movement, trending, flavor])
btn_unload.click(openclip.unload_clip_model)
with gr.Tab("Interrogate Batch"):
with gr.Row():
batch_files = gr.File(label="Files", show_label=True, file_count='multiple', file_types=['image'], type='file', interactive=True, height=100)
with gr.Row():
batch_folder = gr.File(label="Folder", show_label=True, file_count='directory', file_types=['image'], type='file', interactive=True, height=100)
with gr.Row():
batch_str = gr.Text(label="Folder", value="", interactive=True)
with gr.Row():
batch = gr.Text(label="Prompts", lines=10)
with gr.Row():
clip_model = gr.Dropdown([], value='ViT-L-14/openai', label='CLiP Batch Model')
ui_common.create_refresh_button(clip_model, openclip.refresh_clip_models, lambda: {"choices": openclip.refresh_clip_models()}, 'refresh_interrogate_models')
with gr.Row(elem_id='interrogate_buttons_batch'):
btn_interrogate_batch = gr.Button("Interrogate", elem_id="interrogate_btn_interrogate", variant='primary')
with gr.Tab("Visual Query"):
from modules.interrogate import vqa
with gr.Row():
vqa_image = gr.Image(type='pil', label="Image")
with gr.Row():
vqa_question = gr.Dropdown(label="Question", allow_custom_value=True, choices=vqa.vlm_prompts, value=vqa.vlm_prompts[2])
with gr.Row():
vqa_answer = gr.Textbox(label="Answer", lines=5)
with gr.Row(elem_id='interrogate_buttons_query'):
vqa_model = gr.Dropdown(list(vqa.vlm_models), value=list(vqa.vlm_models)[0], label='VLM Model')
vqa_submit = gr.Button("Interrogate", elem_id="interrogate_btn_interrogate", variant='primary')
vqa_submit.click(vqa.interrogate, inputs=[vqa_question, vqa_image, vqa_model], outputs=[vqa_answer])
with gr.Row():
save_output = gr.Checkbox(label='Save output', value=True, elem_id="extras_save_output")
with gr.Row():
save_output = gr.Checkbox(label='Save output', value=True, elem_id="extras_save_output")
script_inputs = scripts.scripts_postproc.setup_ui()
with gr.Column():
@@ -114,20 +45,18 @@ def create_ui():
gr.HTML('File metadata')
exif_info = gr.HTML(elem_id="pnginfo_html_info")
gen_info = gr.Text(elem_id="pnginfo_gen_info", visible=False)
with gr.Row(elem_id='copy_buttons_process'):
copy_process_buttons = generation_parameters_copypaste.create_buttons(["txt2img", "img2img", "control", "caption"])
for tabname, button in copy_process_buttons.items():
generation_parameters_copypaste.register_paste_params_button(generation_parameters_copypaste.ParamBinding(paste_button=button, tabname=tabname, source_text_component=gen_info, source_image_component=extras_image))
for tabname, button in copy_interrogate_buttons.items():
generation_parameters_copypaste.register_paste_params_button(generation_parameters_copypaste.ParamBinding(paste_button=button, tabname=tabname, source_text_component=prompt, source_image_component=image,))
generation_parameters_copypaste.add_paste_fields("extras", extras_image, None)
tab_single.select(fn=lambda: 0, inputs=[], outputs=[tab_index])
tab_batch.select(fn=lambda: 1, inputs=[], outputs=[tab_index])
tab_batch_dir.select(fn=lambda: 2, inputs=[], outputs=[tab_index])
extras_image.change(
fn=wrap_gradio_call(submit_info),
inputs=[extras_image],
outputs=[html_info_formatted, exif_info, gen_info],
)
extras_image.change(fn=submit_info, inputs=[extras_image], outputs=[html_info_formatted, exif_info, gen_info])
extras_image.change(fn=scripts.scripts_postproc.image_changed, inputs=[], outputs=[])
submit.click(
_js="submit_postprocessing",
fn=call_queue.wrap_gradio_gpu_call(submit_process, extra_outputs=[None, ''], name='Postprocess'),
@@ -148,15 +77,3 @@ def create_ui():
html_log,
]
)
btn_interrogate_batch.click(
fn=openclip.interrogate_batch,
inputs=[batch_files, batch_folder, batch_str, clip_model, blip_model, mode, save_output],
outputs=[batch],
)
generation_parameters_copypaste.add_paste_fields("extras", extras_image, None)
extras_image.change(
fn=scripts.scripts_postproc.image_changed,
inputs=[], outputs=[]
)