Merge pull request #2324 from HunterVacui/interrogate_include_ranks_in_output

Interrogate: add option to include ranks in output

modules/deepbooru.py

@@ -19,6 +19,7 @@ def get_deepbooru_tags(pil_image):
         release_process()
 
 
+OPT_INCLUDE_RANKS = "include_ranks"
 def create_deepbooru_opts():
     from modules import shared
 
@@ -26,6 +27,7 @@ def create_deepbooru_opts():
         "use_spaces": shared.opts.deepbooru_use_spaces,
         "use_escape": shared.opts.deepbooru_escape,
         "alpha_sort": shared.opts.deepbooru_sort_alpha,
+        OPT_INCLUDE_RANKS: shared.opts.interrogate_return_ranks,
     }
 
 
@@ -113,6 +115,7 @@ def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, deepbooru_o
     alpha_sort = deepbooru_opts['alpha_sort']
     use_spaces = deepbooru_opts['use_spaces']
     use_escape = deepbooru_opts['use_escape']
+    include_ranks = deepbooru_opts['include_ranks']
 
     width = model.input_shape[2]
     height = model.input_shape[1]
@@ -151,19 +154,20 @@ def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, deepbooru_o
     if alpha_sort:
         sort_ndx = 1
 
-    # sort by reverse by likelihood and normal for alpha
+    # sort by reverse by likelihood and normal for alpha, and format tag text as requested
     unsorted_tags_in_theshold.sort(key=lambda y: y[sort_ndx], reverse=(not alpha_sort))
     for weight, tag in unsorted_tags_in_theshold:
-        result_tags_out.append(tag)
+        # note: tag_outformat will still have a colon if include_ranks is True
+        tag_outformat = tag.replace(':', ' ')
+        if use_spaces:
+            tag_outformat = tag_outformat.replace('_', ' ')
+        if use_escape:
+            tag_outformat = re.sub(re_special, r'\\\1', tag_outformat)
+        if include_ranks:
+            tag_outformat += f":{weight:.3f}"
 
-    print('\n'.join(sorted(result_tags_print, reverse=True)))
-
-    tags_text = ', '.join(result_tags_out)
+        result_tags_out.append(tag_outformat)
 
-    if use_spaces:
-        tags_text = tags_text.replace('_', ' ')
-
-    if use_escape:
-        tags_text = re.sub(re_special, r'\\\1', tags_text)
+    print('\n'.join(sorted(result_tags_print, reverse=True)))
 
-    return tags_text.replace(':', ' ')
+    return ', '.join(result_tags_out)

modules/interrogate.py

@@ -123,7 +123,7 @@ class InterrogateModels:
 
         return caption[0]
 
-    def interrogate(self, pil_image):
+    def interrogate(self, pil_image, include_ranks=False):
         res = None
 
         try:
@@ -156,7 +156,10 @@ class InterrogateModels:
                 for name, topn, items in self.categories:
                     matches = self.rank(image_features, items, top_count=topn)
                     for match, score in matches:
-                        res += ", " + match
+                        if include_ranks:
+                            res += ", " + match
+                        else:
+                            res += f", ({match}:{score})"
 
         except Exception:
             print(f"Error interrogating", file=sys.stderr)

modules/shared.py

@@ -255,6 +255,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
 options_templates.update(options_section(('interrogate', "Interrogate Options"), {
     "interrogate_keep_models_in_memory": OptionInfo(False, "Interrogate: keep models in VRAM"),
     "interrogate_use_builtin_artists": OptionInfo(True, "Interrogate: use artists from artists.csv"),
+    "interrogate_return_ranks": OptionInfo(False, "Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators)."),
     "interrogate_clip_num_beams": OptionInfo(1, "Interrogate: num_beams for BLIP", gr.Slider, {"minimum": 1, "maximum": 16, "step": 1}),
     "interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}),
     "interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}),

modules/textual_inversion/preprocess.py

@@ -17,7 +17,9 @@ def preprocess(process_src, process_dst, process_width, process_height, process_
             shared.interrogator.load()
 
         if process_caption_deepbooru:
-            deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, deepbooru.create_deepbooru_opts())
+            db_opts = deepbooru.create_deepbooru_opts()
+            db_opts[deepbooru.OPT_INCLUDE_RANKS] = False
+            deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, db_opts)
 
         preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru)