Merge b1ff036a22 into 51bf508a0b

* fix(Video): don't crash on videos with undecodable audio streams

Signed-off-by: bigcat88 <bigcat88@icloud.com>

* Update comfy_api_nodes/util/upload_helpers.py

---------

Signed-off-by: bigcat88 <bigcat88@icloud.com>
Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>

comfy/model_management.py

@@ -432,6 +432,98 @@ def is_amd():
             return True
     return False
 
+def is_integrated_gpu(device=None):
+    # AMD APUs / integrated GPUs expose host RAM (GTT/shared) as device memory
+    # via mem_get_info(); torch flags these as integrated. See ComfyUI #14274.
+    if cpu_state != CPUState.GPU:
+        return False
+    if not (is_nvidia() or is_amd()):
+        return False
+    try:
+        if device is None:
+            device = get_torch_device()
+        return bool(getattr(torch.cuda.get_device_properties(device), "is_integrated", 0))
+    except Exception:
+        return False
+
+def _amd_vram_gtt_totals(device=None):
+    # Best-effort (vram_total, gtt_total) in bytes from the amdgpu sysfs nodes
+    # mem_info_vram_total / mem_info_gtt_total, or None when they cannot be read
+    # (e.g. NVIDIA Tegra integrated parts that have no dedicated VRAM). #14274
+    if not is_amd():
+        return None
+    try:
+        drm_root = "/sys/class/drm"
+        candidates = []
+        for name in os.listdir(drm_root):
+            if not (name.startswith("card") and name[len("card"):].isdigit()):
+                continue
+            dev_dir = os.path.join(drm_root, name, "device")
+            vram_path = os.path.join(dev_dir, "mem_info_vram_total")
+            gtt_path = os.path.join(dev_dir, "mem_info_gtt_total")
+            if not (os.path.exists(vram_path) and os.path.exists(gtt_path)):
+                continue
+            try:
+                with open(os.path.join(dev_dir, "vendor")) as vf:
+                    if vf.read().strip().lower() != "0x1002":
+                        continue
+            except OSError:
+                pass
+            candidates.append((os.path.basename(os.path.realpath(dev_dir)), vram_path, gtt_path))
+        if not candidates:
+            return None
+        chosen = None
+        target_bdf = None
+        try:
+            if device is None:
+                device = get_torch_device()
+            props = torch.cuda.get_device_properties(device)
+            # torch reports the PCI location as integers (pci_domain_id / pci_bus_id
+            # / pci_device_id); amdgpu names its sysfs nodes as a hex
+            # "domain:bus:device.function" BDF. Build the canonical hex BDF so the
+            # two are comparable (the old str(pci_bus_id) compared a decimal bus
+            # number against a hex BDF string and could never match). #14274
+            target_bdf = "%04x:%02x:%02x" % (
+                int(getattr(props, "pci_domain_id", 0) or 0),
+                int(getattr(props, "pci_bus_id", 0) or 0),
+                int(getattr(props, "pci_device_id", 0) or 0),
+            )
+        except Exception:
+            target_bdf = None
+        if target_bdf:
+            for pci, vram_path, gtt_path in candidates:
+                # candidates carry the realpath() leaf BDF (domain:bus:device.function),
+                # so matching the domain:bus:device part works whether the GPU is
+                # attached directly or sits behind a PCIe bridge (nested sysfs path). #14274
+                if pci.lower().rsplit(".", 1)[0] == target_bdf:
+                    chosen = (vram_path, gtt_path)
+                    break
+        if chosen is None and len(candidates) == 1:
+            chosen = (candidates[0][1], candidates[0][2])
+        if chosen is None:
+            return None
+        with open(chosen[0]) as f:
+            vram_total = int(f.read().strip())
+        with open(chosen[1]) as f:
+            gtt_total = int(f.read().strip())
+        return (vram_total, gtt_total)
+    except Exception:
+        return None
+
+def integrated_gpu_is_shared_heavy(device=None):
+    # For an integrated GPU, decide whether its memory is dominated by the shared
+    # GTT/host-RAM aperture (treat as UMA -> SHARED) or by a large dedicated VRAM
+    # carveout (keep NORMAL/HIGH_VRAM). Keys on the amdgpu mem_info_vram_total vs
+    # mem_info_gtt_total ratio (ComfyUI #14274). Defaults to True when the totals
+    # are unavailable (e.g. NVIDIA Tegra parts that have no dedicated VRAM).
+    totals = _amd_vram_gtt_totals(device)
+    if totals is None:
+        return True
+    vram_total, gtt_total = totals
+    if not vram_total or vram_total <= 0:
+        return True
+    return gtt_total >= vram_total
+
 def amd_min_version(device=None, min_rdna_version=0):
     if not is_amd():
         return False
@@ -569,6 +661,15 @@ if cpu_state != CPUState.GPU:
 if cpu_state == CPUState.MPS:
     vram_state = VRAMState.SHARED
 
+if vram_state == VRAMState.NORMAL_VRAM and is_integrated_gpu() and integrated_gpu_is_shared_heavy():
+    # Integrated/UMA GPU whose shared GTT/host-RAM pool dominates the (small)
+    # dedicated VRAM carveout: treat as UMA and use SHARED so the shared pool is
+    # not double-counted as dedicated VRAM (#14274). Dedicated-heavy integrated
+    # parts (large BIOS UMA carveout, e.g. Strix Halo) keep NORMAL_VRAM where
+    # HIGH_VRAM is correct.
+    vram_state = VRAMState.SHARED
+    logging.info("Integrated GPU with shared-memory-dominant pool detected (UMA): using SHARED vram state to avoid double-counting GTT/shared memory as dedicated VRAM.")
+
 logging.info(f"Set vram state to: {vram_state.name}")
 
 DISABLE_SMART_MEMORY = args.disable_smart_memory

comfy_api/latest/_input_impl/video_types.py

@@ -281,11 +281,18 @@ class VideoFromFile(VideoInput):
         video_done = False
         audio_done = True
 
-        if len(container.streams.audio):
-            audio_stream = container.streams.audio[-1]
+        # Use the last decodable audio stream. Streams FFmpeg has no decoder for have no codec context,
+        # and decoding their packets crashes the process. (e.g. APAC spatial-audio track in iPhone)
+        audio_stream = next(
+            (s for s in reversed(container.streams.audio) if s.codec_context is not None),
+            None,
+        )
+        if audio_stream is not None:
             streams += [audio_stream]
             resampler = av.audio.resampler.AudioResampler(format='fltp')
             audio_done = False
+        elif len(container.streams.audio):
+            logging.warning("No decodable audio stream found in video; ignoring audio.")
 
         for packet in container.demux(*streams):
             if video_done and audio_done:
@@ -457,10 +464,13 @@ class VideoFromFile(VideoInput):
                         else:
                             output_container.metadata[key] = json.dumps(value)
 
-                # Add streams to the new container
+                # Add streams to the new container. Streams with no codec context cannot be used as an output template.
                 stream_map = {}
                 for stream in streams:
                     if isinstance(stream, (av.VideoStream, av.AudioStream, SubtitleStream)):
+                        if stream.codec_context is None:
+                            logging.warning("Skipping %s stream %d with unsupported codec", stream.type, stream.index)
+                            continue
                         out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
                         stream_map[stream] = out_stream
 

comfy_api_nodes/util/upload_helpers.py

@@ -158,7 +158,14 @@ async def upload_video_to_comfyapi(
 
     # Convert VideoInput to BytesIO using specified container/codec
     video_bytes_io = BytesIO()
-    video.save_to(video_bytes_io, format=container, codec=codec)
+    try:
+        video.save_to(video_bytes_io, format=container, codec=codec)
+    except Exception as e:
+        raise ValueError(
+            f"Could not convert the input video to {container.value.upper()} for upload; "
+            f"the file may be corrupted or use an unsupported codec. "
+            f"Try re-exporting it as MP4 (H.264). Original error: {e}"
+        ) from e
     video_bytes_io.seek(0)
 
     return await upload_file_to_comfyapi(cls, video_bytes_io, filename, upload_mime_type, wait_label)

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",