diff --git a/modules/config.py b/modules/config.py index bcdba536..92bc129a 100644 --- a/modules/config.py +++ b/modules/config.py @@ -418,13 +418,7 @@ embeddings_downloads = get_config_item_or_set_default( ) available_aspect_ratios = get_config_item_or_set_default( key='available_aspect_ratios', - default_value=[ - '704*1408', '704*1344', '768*1344', '768*1280', '832*1216', '832*1152', - '896*1152', '896*1088', '960*1088', '960*1024', '1024*1024', '1024*960', - '1088*960', '1088*896', '1152*896', '1152*832', '1216*832', '1280*768', - '1344*768', '1344*704', '1408*704', '1472*704', '1536*640', '1600*640', - '1664*576', '1728*576' - ], + default_value=modules.flags.sdxl_aspect_ratios, validator=lambda x: isinstance(x, list) and all('*' in v for v in x) and len(x) > 1 ) default_aspect_ratio = get_config_item_or_set_default( @@ -556,7 +550,7 @@ def add_ratio(x): default_aspect_ratio = add_ratio(default_aspect_ratio) -available_aspect_ratios = [add_ratio(x) for x in available_aspect_ratios] +available_aspect_ratios_labels = [add_ratio(x) for x in available_aspect_ratios] # Only write config in the first launch. diff --git a/modules/flags.py b/modules/flags.py index a406af4f..0ae44375 100644 --- a/modules/flags.py +++ b/modules/flags.py @@ -85,6 +85,13 @@ inpaint_options = [inpaint_option_default, inpaint_option_detail, inpaint_option desc_type_photo = 'Photograph' desc_type_anime = 'Art/Anime' +sdxl_aspect_ratios = [ + '704*1408', '704*1344', '768*1344', '768*1280', '832*1216', '832*1152', + '896*1152', '896*1088', '960*1088', '960*1024', '1024*1024', '1024*960', + '1088*960', '1088*896', '1152*896', '1152*832', '1216*832', '1280*768', + '1344*768', '1344*704', '1408*704', '1472*704', '1536*640', '1600*640', + '1664*576', '1728*576' +] class MetadataScheme(Enum): FOOOCUS = 'fooocus' diff --git a/modules/meta_parser.py b/modules/meta_parser.py index d59902e4..261c2f0e 100644 --- a/modules/meta_parser.py +++ b/modules/meta_parser.py @@ -124,7 +124,7 @@ def get_resolution(key: str, fallback: str | None, source_dict: dict, results: l h = source_dict.get(key, source_dict.get(fallback, default)) width, height = eval(h) formatted = modules.config.add_ratio(f'{width}*{height}') - if formatted in modules.config.available_aspect_ratios: + if formatted in modules.config.available_aspect_ratios_labels: results.append(formatted) results.append(-1) results.append(-1) diff --git a/modules/util.py b/modules/util.py index cb5580fb..fba6082f 100644 --- a/modules/util.py +++ b/modules/util.py @@ -467,3 +467,25 @@ def apply_wildcards(wildcard_text, rng, i, read_wildcards_in_order) -> str: print(f'[Wildcards] BFS stack overflow. Current text: {wildcard_text}') return wildcard_text + + +def get_image_size_info(image: np.ndarray, aspect_ratios: list) -> str: + try: + image = Image.fromarray(np.uint8(image)) + width, height = image.size + ratio = round(width / height, 2) + gcd = math.gcd(width, height) + lcm_ratio = f'{width // gcd}:{height // gcd}' + size_info = f'Image Size: {width} x {height}, Ratio: {ratio}, {lcm_ratio}' + + closest_ratio = min(aspect_ratios, key=lambda x: abs(ratio - float(x.split('*')[0]) / float(x.split('*')[1]))) + recommended_width, recommended_height = map(int, closest_ratio.split('*')) + recommended_ratio = round(recommended_width / recommended_height, 2) + recommended_gcd = math.gcd(recommended_width, recommended_height) + recommended_lcm_ratio = f'{recommended_width // recommended_gcd}:{recommended_height // recommended_gcd}' + + size_info += f'\nRecommended Size: {recommended_width} x {recommended_height}, Ratio: {recommended_ratio}, {recommended_lcm_ratio}' + + return size_info + except Exception as e: + return f'Error reading image: {e}' diff --git a/webui.py b/webui.py index 0536f1f6..d076da84 100644 --- a/webui.py +++ b/webui.py @@ -273,7 +273,16 @@ with shared.gradio_root: choices=[flags.desc_type_photo, flags.desc_type_anime], value=flags.desc_type_photo) desc_btn = gr.Button(value='Describe this Image into Prompt') + desc_image_size = gr.Markdown(label='Image Size', elem_id='desc_image_size', visible=False) gr.HTML('\U0001F4D4 Document') + + def trigger_show_image_properties(image): + value = modules.util.get_image_size_info(image, modules.flags.sdxl_aspect_ratios) + return gr.update(value=value, visible=True) + + desc_input_image.upload(trigger_show_image_properties, inputs=desc_input_image, + outputs=desc_image_size, show_progress=False, queue=False) + with gr.TabItem(label='Metadata') as load_tab: with gr.Column(): metadata_input_image = grh.Image(label='Drag any image generated by Fooocus here', source='upload', type='filepath')