Merge 1c93e5f433 into 6880614319

AGENTS.md

@@ -127,6 +127,8 @@
 - Do not add unnecessary `try`/`except` blocks. Use them for optional dependency,
   platform, or backend capability detection only when the program has a useful
   fallback. Prefer specific exception types when changing new code.
+- If a library version is pinned in `requirements.txt`, do not add code to
+  ComfyUI to handle older versions of that library.
 - Remove any workarounds for PyTorch versions that ComfyUI no longer officially
   supports. Deprecated workarounds include catching an exception and rerunning
   the same op with the input cast to float. If a workaround does not have a

comfy/text_encoders/ideogram4.py

@@ -5,6 +5,8 @@ Qwen3-VL (layers 0,3,...,33,35), giving a 4096*13 = 53248-dim feature per token.
 """
 
 import os
+import torch
+import numbers
 
 from transformers import Qwen2Tokenizer
 
@@ -32,14 +34,23 @@ class Ideogram4Tokenizer(sd1_clip.SD1Tokenizer):
 
         self.llama_template = "<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n"
 
-    def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, **kwargs):
+    def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, prevent_empty_text=False, **kwargs):
+        skip_template = False
         if text.startswith('<|im_start|>'):
+            skip_template = True
+        if prevent_empty_text and text == '':
+            text = ' '
+
+        if skip_template:
             llama_text = text
-        elif llama_template is None:
-            llama_text = self.llama_template.format(text)
         else:
-            llama_text = llama_template.format(text)
-        return super().tokenize_with_weights(llama_text, return_word_ids=return_word_ids, disable_weights=True, **kwargs)
+            if llama_template is None:
+                llama_text = self.llama_template.format(text)
+            else:
+                llama_text = llama_template.format(text)
+
+        tokens = super().tokenize_with_weights(llama_text, return_word_ids=return_word_ids, disable_weights=True, **kwargs)
+        return tokens
 
 
 # Qwen3-VL-8B = 5e6 (vs plain Qwen3-8B's 1e6)
@@ -61,10 +72,54 @@ class Ideogram4TEModel(sd1_clip.SD1ClipModel):
     def __init__(self, device="cpu", dtype=None, model_options={}):
         super().__init__(device=device, dtype=dtype, name="qwen3vl_8b", clip_model=Qwen3VL8BModel, model_options=model_options)
 
-    def encode_token_weights(self, token_weight_pairs):
+    def encode_token_weights(self, token_weight_pairs, template_end=0):
         out, pooled, extra = super().encode_token_weights(token_weight_pairs)
         b, n, seq, h = out.shape # (B, n_taps=13, seq, 4096) stacked in ascending layer order.
         out = out.permute(0, 2, 3, 1).reshape(b, seq, h * n) # (B, seq, 4096*13). permute -> (B, seq, H, taps).
+
+        if template_end != 0:
+            tok_pairs = token_weight_pairs["qwen3vl_8b"][0]
+            suffix_start = -1
+
+            if template_end == -1:
+                for i in range(len(tok_pairs) - 2):
+                    t0 = tok_pairs[i][0]
+                    t1 = tok_pairs[i + 1][0]
+                    t2 = tok_pairs[i + 2][0]
+                    if not torch.is_tensor(t0) and isinstance(t0, numbers.Integral) and \
+                       not torch.is_tensor(t1) and isinstance(t1, numbers.Integral) and \
+                       not torch.is_tensor(t2) and isinstance(t2, numbers.Integral):
+                        if t0 == 151644 and t1 == 872 and t2 == 198:
+                            template_end = i + 3
+                            break
+                if template_end == -1:
+                    template_end = 0
+
+            # Scan backward for the <|im_end|> token 151643 to determine suffix_start
+            for i in range(len(tok_pairs) - 1, -1, -1):
+                t = tok_pairs[i][0]
+                if not torch.is_tensor(t) and isinstance(t, numbers.Integral):
+                    if t == 151643:
+                        suffix_start = i
+                        break
+
+            # If template_end resolves to greater than 0:
+            if template_end > 0:
+                out = out[:, template_end:]
+                if "attention_mask" in extra and extra["attention_mask"] is not None:
+                    extra["attention_mask"] = extra["attention_mask"][:, template_end:]
+
+            # If suffix_start is located and we are doing stripping:
+            if suffix_start >= 0:
+                suffix_len = len(tok_pairs) - suffix_start
+                out = out[:, :-suffix_len]
+                if "attention_mask" in extra and extra["attention_mask"] is not None:
+                    extra["attention_mask"] = extra["attention_mask"][:, :-suffix_len]
+
+        if "attention_mask" in extra and extra["attention_mask"] is not None:
+            if extra["attention_mask"].sum() == torch.numel(extra["attention_mask"]):
+                extra.pop("attention_mask")
+
         return out, pooled, extra
 
 

comfy_extras/nodes_text_overlay.py

@@ -0,0 +1,150 @@
+import numpy as np
+import torch
+from PIL import Image as PILImage, ImageColor, ImageDraw, ImageFont
+from typing_extensions import override
+
+from comfy_api.latest import ComfyExtension, IO
+
+
+class TextOverlay(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="TextOverlay",
+            display_name="Draw Text Overlay",
+            category="text",
+            description="Draw text overlay on an image or batch of images.",
+            search_aliases=["text", "label", "caption", "subtitle", "watermark", "title", "addlabel", "overlay"],
+            inputs=[
+                IO.Image.Input("images"),
+                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.Boolean.Input("outline", default=True, tooltip="Draw a black outline around the text."),
+            ],
+            outputs=[IO.Image.Output(display_name="images")],
+        )
+
+    @classmethod
+    def execute(cls, images, text, font_size, color, position, align, outline) -> IO.NodeOutput:
+        if text.strip() == "":
+            return IO.NodeOutput(images)
+
+        text = text.replace("\\n", "\n").replace("\\t", "\t")
+
+        text_rgba = cls.parse_color_to_rgba(color)
+        outline_rgba = (0, 0, 0, 255) if outline else (0, 0, 0, 0)
+
+        # Render the overlay once and composite it across all frames in the batch
+        height = images.shape[1]
+        width = images.shape[2]
+        overlay_rgb, overlay_alpha = cls.render_overlay_text(width, height, text, position, align, font_size, text_rgba, outline_rgba)
+        overlay_rgb = overlay_rgb.to(device=images.device, dtype=images.dtype)
+        overlay_alpha = overlay_alpha.to(device=images.device, dtype=images.dtype)
+
+        result = images * (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, align, font_size, text_rgba, outline_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)
+
+        margin = int(round(margin_percent / 100.0 * min(width, height)))
+        max_width = max(1, width - 2 * margin)
+        max_height = max(1, height - 2 * margin)
+
+        # Font scales with resolution, then shrinks to fit the 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_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)
+            double = draw.multiline_textbbox((0, 0), "Ay\nAy", font=font, spacing=0, stroke_width=stroke)
+            natural_advance = (double[3] - double[1]) - (single[3] - single[1])
+            pixel_spacing = int(round(size * line_spacing - natural_advance))
+            box = draw.multiline_textbbox((0, 0), block, font=font, spacing=pixel_spacing, stroke_width=stroke)
+            block_height = box[3] - box[1]
+
+            if block_height <= max_height or size <= floor:
+                break
+
+            size = max(floor, int(size * 0.9))
+
+        anchor_h, x = {"left": ("l", margin), "center": ("m", width / 2), "right": ("r", width - margin)}[align]
+
+        # Offset y so the rendered text sits flush against the margin
+        if position == "bottom":
+            y = height - margin - box[3]
+        else:
+            y = margin - box[1]
+
+        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])
+        overlay_alpha = torch.from_numpy(overlay[:, :, 3:4])
+        return overlay_rgb, overlay_alpha
+
+    @staticmethod
+    def wrap_text(text, font, max_width):
+        lines = []
+        for raw_line in text.split("\n"):
+            words = raw_line.split()
+            if not words:
+                lines.append("")
+                continue
+            current = ""
+            # Break the line into words and split words that are too long
+            for word in words:
+                while font.getlength(word) > max_width and len(word) > 1:
+                    cut = 1
+                    while cut < len(word) and font.getlength(word[:cut + 1]) <= max_width:
+                        cut += 1
+                    if current:
+                        lines.append(current)
+                        current = ""
+                    lines.append(word[:cut])
+                    word = word[cut:]
+                candidate = word if not current else current + " " + word
+                if not current or font.getlength(candidate) <= max_width:
+                    current = candidate
+                else:
+                    lines.append(current)
+                    current = word
+            if current:
+                lines.append(current)
+        return lines
+
+
+class TextOverlayExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[IO.ComfyNode]]:
+        return [TextOverlay]
+
+
+async def comfy_entrypoint() -> TextOverlayExtension:
+    return TextOverlayExtension()

nodes.py

@@ -2478,6 +2478,7 @@ async def init_builtin_extra_nodes():
         "nodes_glsl.py",
         "nodes_lora_debug.py",
         "nodes_textgen.py",
+        "nodes_text_overlay.py",
         "nodes_color.py",
         "nodes_toolkit.py",
         "nodes_replacements.py",