diff --git a/comfy_extras/nodes_text_overlay.py b/comfy_extras/nodes_text_overlay.py index 416d7ced7..fad4e050c 100644 --- a/comfy_extras/nodes_text_overlay.py +++ b/comfy_extras/nodes_text_overlay.py @@ -11,65 +11,76 @@ class TextOverlay(IO.ComfyNode): def define_schema(cls): return IO.Schema( node_id="TextOverlay", - display_name="Text Overlay", - category="image/text", - description="Overlay text on an image or batch of images.", + display_name="Draw Text Overlay", + category="text", + description="Draw overlay text on an image or batch of images.", search_aliases=["text", "label", "caption", "subtitle", "watermark", "title", "addlabel", "overlay"], inputs=[ IO.Image.Input("image"), IO.String.Input("text", multiline=True, default=""), + IO.Float.Input("font_size", default=5.0, min=0.5, max=50.0, step=0.5, tooltip="Font size as a percentage of the image height."), + IO.Color.Input("color", default="#ffffff", tooltip="Color of the text."), IO.Combo.Input("position", options=["top", "bottom"], default="top"), IO.Combo.Input("align", options=["left", "center", "right"], default="left"), - IO.Float.Input("font_size_percent", default=5.0, min=0.5, max=50.0, step=0.5, tooltip="Font size as a percentage of the image height.", advanced=True), - #IO.Combo.Input("text_color", options=["white", "black", "red", "green", "blue", "yellow", "cyan", "magenta", "gray"], default="white", tooltip="Color of the text.", advanced=True), - #IO.Combo.Input("outline_color", options=["auto", "none", "black", "white", "red", "green", "blue", "yellow"], default="auto", tooltip="Color of the text outline.", advanced=True), - #IO.Float.Input("background_opacity", default=0.0, min=0.0, max=1.0, step=0.05, tooltip="Opacity of the background behind the text (0 = transparent, 1 = solid).", advanced=True), + IO.Boolean.Input("outline", default=True, tooltip="Draw a black outline around the text."), + IO.DynamicCombo.Input( + "background", + tooltip="Draw a banner behind the text to improve contrast.", + options=[ + IO.DynamicCombo.Option("disabled", []), + IO.DynamicCombo.Option("enabled", [ + IO.Color.Input("background_color", default="#00000080", tooltip="Color of the banner drawn behind the text. The color's opacity controls the banner transparency."), + ]), + ], + ), ], outputs=[IO.Image.Output()], ) @classmethod - def execute(cls, image, text, position="top", align="left", font_size_percent=5.0, text_color="white", outline_color="auto", - line_spacing=1.2, background_opacity=0.0) -> IO.NodeOutput: + def execute(cls, image, text, font_size, color, position, align, outline, background) -> IO.NodeOutput: if text.strip() == "": return IO.NodeOutput(image) text = text.replace("\\n", "\n").replace("\\t", "\t") - try: - text_rgb = ImageColor.getrgb(text_color)[:3] - except ValueError: - text_rgb = (255, 255, 255) + text_rgba = cls.parse_color_to_rgba(color) + outline_rgba = (0, 0, 0, 255) if outline else (0, 0, 0, 0) - # "auto" outline color: set the outline color based on text color to maintain contrast - luminance = 0.299 * text_rgb[0] + 0.587 * text_rgb[1] + 0.114 * text_rgb[2] - contrast_rgb = (0, 0, 0) if luminance > 40 else (255, 255, 255) - outline_choice = outline_color.lower() - - if outline_choice == "none": - outline_rgb = None - elif outline_choice == "auto": - outline_rgb = contrast_rgb + # The background banner opacity is set by the color's alpha channel, 50% by default + if background["background"] == "enabled": + background_rgba = cls.parse_color_to_rgba(background["background_color"]) else: - outline_rgb = ImageColor.getrgb(outline_color)[:3] - - background_rgb = contrast_rgb if outline_rgb is None else outline_rgb + background_rgba = (0, 0, 0, 0) # Render the overlay once and composite it across all frames in the batch - height = int(image.shape[1]) - width = int(image.shape[2]) - overlay_rgb, overlay_alpha = cls.render_overlay_text(width, height, text, position, align, font_size_percent, - text_rgb, outline_rgb, background_rgb, line_spacing, background_opacity) + height = image.shape[1] + width = image.shape[2] + overlay_rgb, overlay_alpha = cls.render_overlay_text(width, height, text, position, align, font_size, + text_rgba, outline_rgba, background_rgba) overlay_rgb = overlay_rgb.to(device=image.device, dtype=image.dtype) overlay_alpha = overlay_alpha.to(device=image.device, dtype=image.dtype) result = image * (1.0 - overlay_alpha) + overlay_rgb * overlay_alpha return IO.NodeOutput(result) + @staticmethod + def parse_color_to_rgba(color_string): + parsed = ImageColor.getrgb(color_string) + + if len(parsed) == 3: + return (*parsed, 255) + + return parsed + @classmethod - def render_overlay_text(cls, width, height, text, position="top", align="left", font_size_percent=5.0, - text_rgb=(255, 255, 255), outline_rgb=None, background_rgb=None, line_spacing=1.2, background_opacity=0.0, - margin_percent=1.0, min_font_percent=2.0, min_font_pixels=10, outline_thickness_factor=0.04): + def render_overlay_text(cls, width, height, text, position, align, font_size, text_rgba, outline_rgba, background_rgba): + line_spacing = 1.2 + margin_percent = 1.0 + min_font_percent = 2.0 + min_font_pixels = 10 + outline_thickness_factor = 0.04 + # Draw onto a transparent layer so the result can be alpha-composited over any frame. layer = PILImage.new("RGBA", (width, height), (0, 0, 0, 0)) draw = ImageDraw.Draw(layer) @@ -79,12 +90,12 @@ class TextOverlay(IO.ComfyNode): max_height = max(1, height - 2 * margin) # Font scales with resolution, then shrinks to fit the height. - size = max(1, int(round(font_size_percent / 100.0 * height))) + size = max(1, int(round(font_size / 100.0 * height))) floor = min(size, max(min_font_pixels, int(round(min_font_percent / 100.0 * height)))) while True: font = ImageFont.load_default(size=size) - stroke = max(1, int(round(size * outline_thickness_factor))) if outline_rgb is not None else 0 + stroke = max(1, int(round(size * outline_thickness_factor))) if outline_rgba[3] > 0 else 0 block = "\n".join(cls.wrap_text(text, font, max_width)) # convert line spacing to pixel spacing single = draw.textbbox((0, 0), "Ay", font=font, stroke_width=stroke) @@ -99,20 +110,21 @@ class TextOverlay(IO.ComfyNode): size = max(floor, int(size * 0.9)) - if background_opacity > 0: + if background_rgba[3] > 0: band = block_height + 2 * margin rect = [0, height - band, width, height] if position == "bottom" else [0, 0, width, band] - draw.rectangle(rect, fill=(*background_rgb, int(round(background_opacity * 255)))) + draw.rectangle(rect, fill=background_rgba) anchor_h, x = {"left": ("l", margin), "center": ("m", width / 2), "right": ("r", width - margin)}[align] + # Offset y to better center text vertically within its defined band if position == "bottom": - anchor_v, y = "d", height - margin + y = height - margin - box[3] else: - anchor_v, y = "a", margin + y = margin - box[1] - draw.multiline_text((x, y), block, font=font, fill=text_rgb, anchor=anchor_h + anchor_v, - align=align, spacing=pixel_spacing, stroke_width=stroke, stroke_fill=outline_rgb) + draw.multiline_text((x, y), block, font=font, fill=text_rgba, anchor=anchor_h + "a", + align=align, spacing=pixel_spacing, stroke_width=stroke, stroke_fill=outline_rgba) overlay = np.array(layer).astype(np.float32) / 255.0 overlay_rgb = torch.from_numpy(overlay[:, :, :3])