Merge 5e7ba5fc55 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/ldm/chroma_radiance/model.py

@@ -9,12 +9,13 @@ import torch
 from torch import Tensor, nn
 from einops import repeat
 import comfy.ldm.common_dit
+import comfy.patcher_extension
 
-from comfy.ldm.flux.layers import EmbedND, DoubleStreamBlock, SingleStreamBlock
+from comfy.ldm.flux.layers import EmbedND, timestep_embedding, DoubleStreamBlock, SingleStreamBlock
 
-from comfy.ldm.chroma.model import Chroma, ChromaParams
 from comfy.ldm.chroma.layers import (
     Approximator,
+    ChromaModulationOut,
 )
 from .layers import (
     NerfEmbedder,
@@ -25,7 +26,26 @@ from .layers import (
 
 
 @dataclass
-class ChromaRadianceParams(ChromaParams):
+class ChromaRadianceParams:
+    # Fields from ChromaParams (now independent)
+    in_channels: int
+    out_channels: int
+    context_in_dim: int
+    hidden_size: int
+    mlp_ratio: float
+    num_heads: int
+    depth: int
+    depth_single_blocks: int
+    axes_dim: list
+    theta: int
+    qkv_bias: bool
+    in_dim: int
+    out_dim: int
+    hidden_dim: int
+    n_layers: int
+    txt_ids_dims: list
+    vec_in_dim: int
+    # ChromaRadiance-specific fields
     patch_size: int
     nerf_hidden_size: int
     nerf_mlp_ratio: int
@@ -41,7 +61,7 @@ class ChromaRadianceParams(ChromaParams):
     # Use sequential txt_ids instead of zeros
     use_sequential_txt_ids: bool
 
-class ChromaRadiance(Chroma):
+class ChromaRadiance(nn.Module):
     """
     Transformer model for flow matching on sequences.
     """
@@ -49,7 +69,7 @@ class ChromaRadiance(Chroma):
     def __init__(self, image_model=None, final_layer=True, dtype=None, device=None, operations=None, **kwargs):
         if operations is None:
             raise RuntimeError("Attempt to create ChromaRadiance object without setting operations")
-        nn.Module.__init__(self)
+        super().__init__()
         self.dtype = dtype
         params = ChromaRadianceParams(**kwargs)
         self.params = params
@@ -181,6 +201,155 @@ class ChromaRadiance(Chroma):
         # flatten into a sequence for the transformer.
         return img.flatten(2).transpose(1, 2) # -> [B, NumPatches, Hidden]
 
+    def get_modulations(self, tensor: torch.Tensor, block_type: str, *, idx: int = 0):
+        # This function slices up the modulations tensor which has the following layout:
+        #   single     : num_single_blocks * 3 elements
+        #   double_img : num_double_blocks * 6 elements
+        #   double_txt : num_double_blocks * 6 elements
+        #   final      : 2 elements
+        if block_type == "final":
+            return (tensor[:, -2:-1, :], tensor[:, -1:, :])
+        single_block_count = self.params.depth_single_blocks
+        double_block_count = self.params.depth
+        offset = 3 * idx
+        if block_type == "single":
+            return ChromaModulationOut.from_offset(tensor, offset)
+        # Double block modulations are 6 elements so we double 3 * idx.
+        offset *= 2
+        if block_type in {"double_img", "double_txt"}:
+            # Advance past the single block modulations.
+            offset += 3 * single_block_count
+            if block_type == "double_txt":
+                # Advance past the double block img modulations.
+                offset += 6 * double_block_count
+            return (
+                ChromaModulationOut.from_offset(tensor, offset),
+                ChromaModulationOut.from_offset(tensor, offset + 3),
+            )
+        raise ValueError("Bad block_type")
+
+    def forward_orig(
+        self,
+        img: Tensor,
+        img_ids: Tensor,
+        txt: Tensor,
+        txt_ids: Tensor,
+        timesteps: Tensor,
+        guidance: Tensor = None,
+        control = None,
+        transformer_options={},
+        attn_mask: Tensor = None,
+    ) -> Tensor:
+        patches_replace = transformer_options.get("patches_replace", {})
+
+        # running on sequences img
+        img = self.img_in(img)
+
+        # distilled vector guidance
+        mod_index_length = 344
+        distill_timestep = timestep_embedding(timesteps.detach().clone(), 16).to(img.device, img.dtype)
+        # guidance = guidance *
+        distil_guidance = timestep_embedding(guidance.detach().clone(), 16).to(img.device, img.dtype)
+
+        # get all modulation index
+        modulation_index = timestep_embedding(torch.arange(mod_index_length, device=img.device), 32).to(img.device, img.dtype)
+        # we need to broadcast the modulation index here so each batch has all of the index
+        modulation_index = modulation_index.unsqueeze(0).repeat(img.shape[0], 1, 1).to(img.device, img.dtype)
+        # and we need to broadcast timestep and guidance along too
+        timestep_guidance = torch.cat([distill_timestep, distil_guidance], dim=1).unsqueeze(1).repeat(1, mod_index_length, 1).to(img.dtype).to(img.device, img.dtype)
+        # then and only then we could concatenate it together
+        input_vec = torch.cat([timestep_guidance, modulation_index], dim=-1).to(img.device, img.dtype)
+
+        mod_vectors = self.distilled_guidance_layer(input_vec)
+
+        txt = self.txt_in(txt)
+
+        ids = torch.cat((txt_ids, img_ids), dim=1)
+        pe = self.pe_embedder(ids)
+
+        blocks_replace = patches_replace.get("dit", {})
+        transformer_options["total_blocks"] = len(self.double_blocks)
+        transformer_options["block_type"] = "double"
+        for i, block in enumerate(self.double_blocks):
+            transformer_options["block_index"] = i
+            if i not in self.skip_mmdit:
+                double_mod = (
+                    self.get_modulations(mod_vectors, "double_img", idx=i),
+                    self.get_modulations(mod_vectors, "double_txt", idx=i),
+                )
+                if ("double_block", i) in blocks_replace:
+                    def block_wrap(args):
+                        out = {}
+                        out["img"], out["txt"] = block(img=args["img"],
+                                                       txt=args["txt"],
+                                                       vec=args["vec"],
+                                                       pe=args["pe"],
+                                                       attn_mask=args.get("attn_mask"),
+                                                       transformer_options=args.get("transformer_options"))
+                        return out
+
+                    out = blocks_replace[("double_block", i)]({"img": img,
+                                                               "txt": txt,
+                                                               "vec": double_mod,
+                                                               "pe": pe,
+                                                               "attn_mask": attn_mask,
+                                                               "transformer_options": transformer_options},
+                                                              {"original_block": block_wrap})
+                    txt = out["txt"]
+                    img = out["img"]
+                else:
+                    img, txt = block(img=img,
+                                     txt=txt,
+                                     vec=double_mod,
+                                     pe=pe,
+                                     attn_mask=attn_mask,
+                                     transformer_options=transformer_options)
+
+                if control is not None: # Controlnet
+                    control_i = control.get("input")
+                    if i < len(control_i):
+                        add = control_i[i]
+                        if add is not None:
+                            img += add
+
+        img = torch.cat((txt, img), 1)
+
+        transformer_options["total_blocks"] = len(self.single_blocks)
+        transformer_options["block_type"] = "single"
+        for i, block in enumerate(self.single_blocks):
+            transformer_options["block_index"] = i
+            if i not in self.skip_dit:
+                single_mod = self.get_modulations(mod_vectors, "single", idx=i)
+                if ("single_block", i) in blocks_replace:
+                    def block_wrap(args):
+                        out = {}
+                        out["img"] = block(args["img"],
+                                           vec=args["vec"],
+                                           pe=args["pe"],
+                                           attn_mask=args.get("attn_mask"),
+                                           transformer_options=args.get("transformer_options"))
+                        return out
+
+                    out = blocks_replace[("single_block", i)]({"img": img,
+                                                               "vec": single_mod,
+                                                               "pe": pe,
+                                                               "attn_mask": attn_mask,
+                                                               "transformer_options": transformer_options},
+                                                              {"original_block": block_wrap})
+                    img = out["img"]
+                else:
+                    img = block(img, vec=single_mod, pe=pe, attn_mask=attn_mask, transformer_options=transformer_options)
+
+                if control is not None: # Controlnet
+                    control_o = control.get("output")
+                    if i < len(control_o):
+                        add = control_o[i]
+                        if add is not None:
+                            img[:, txt.shape[1] :, ...] += add
+
+        img = img[:, txt.shape[1] :, ...]
+        return img
+
     def forward_nerf(
         self,
         img_orig: Tensor,
@@ -290,6 +459,13 @@ class ChromaRadiance(Chroma):
         eps = 0.0
         return (noisy - predicted) / (timesteps.view(-1,1,1,1) + eps)
 
+    def forward(self, x, timestep, context, guidance, control=None, transformer_options={}, **kwargs):
+        return comfy.patcher_extension.WrapperExecutor.new_class_executor(
+            self._forward,
+            self,
+            comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options)
+        ).execute(x, timestep, context, guidance, control, transformer_options, **kwargs)
+
     def _forward(
         self,
         x: Tensor,
@@ -340,4 +516,3 @@ class ChromaRadiance(Chroma):
         if hasattr(self, "__x0__"):
             out = self._apply_x0_residual(out, img, timestep)
         return out
-

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",