Merge branch 'master' into v3-definition-wip

This commit is contained in:
Jedrzej Kosinski
2025-06-26 12:45:20 -07:00
30 changed files with 152649 additions and 60 deletions

View File

@@ -0,0 +1,26 @@
import node_helpers
class ReferenceLatent:
@classmethod
def INPUT_TYPES(s):
return {"required": {"conditioning": ("CONDITIONING", ),
},
"optional": {"latent": ("LATENT", ),}
}
RETURN_TYPES = ("CONDITIONING",)
FUNCTION = "append"
CATEGORY = "advanced/conditioning/edit_models"
DESCRIPTION = "This node sets the guiding latent for an edit model. If the model supports it you can chain multiple to set multiple reference images."
def append(self, conditioning, latent=None):
if latent is not None:
conditioning = node_helpers.conditioning_set_values(conditioning, {"reference_latents": [latent["samples"]]}, append=True)
return (conditioning, )
NODE_CLASS_MAPPINGS = {
"ReferenceLatent": ReferenceLatent,
}

View File

@@ -1,4 +1,5 @@
import node_helpers
import comfy.utils
class CLIPTextEncodeFlux:
@classmethod
@@ -56,8 +57,52 @@ class FluxDisableGuidance:
return (c, )
PREFERED_KONTEXT_RESOLUTIONS = [
(672, 1568),
(688, 1504),
(720, 1456),
(752, 1392),
(800, 1328),
(832, 1248),
(880, 1184),
(944, 1104),
(1024, 1024),
(1104, 944),
(1184, 880),
(1248, 832),
(1328, 800),
(1392, 752),
(1456, 720),
(1504, 688),
(1568, 672),
]
class FluxKontextImageScale:
@classmethod
def INPUT_TYPES(s):
return {"required": {"image": ("IMAGE", ),
},
}
RETURN_TYPES = ("IMAGE",)
FUNCTION = "scale"
CATEGORY = "advanced/conditioning/flux"
DESCRIPTION = "This node resizes the image to one that is more optimal for flux kontext."
def scale(self, image):
width = image.shape[2]
height = image.shape[1]
aspect_ratio = width / height
_, width, height = min((abs(aspect_ratio - w / h), w, h) for w, h in PREFERED_KONTEXT_RESOLUTIONS)
image = comfy.utils.common_upscale(image.movedim(-1, 1), width, height, "lanczos", "center").movedim(1, -1)
return (image, )
NODE_CLASS_MAPPINGS = {
"CLIPTextEncodeFlux": CLIPTextEncodeFlux,
"FluxGuidance": FluxGuidance,
"FluxDisableGuidance": FluxDisableGuidance,
"FluxKontextImageScale": FluxKontextImageScale,
}

View File

@@ -304,10 +304,23 @@ Optional spacing can be added between images.
image2.movedim(-1, 1), target_w, target_h, "lanczos", "disabled"
).movedim(1, -1)
color_map = {
"white": 1.0,
"black": 0.0,
"red": (1.0, 0.0, 0.0),
"green": (0.0, 1.0, 0.0),
"blue": (0.0, 0.0, 1.0),
}
color_val = color_map[spacing_color]
# When not matching sizes, pad to align non-concat dimensions
if not match_image_size:
h1, w1 = image1.shape[1:3]
h2, w2 = image2.shape[1:3]
pad_value = 0.0
if not isinstance(color_val, tuple):
pad_value = color_val
if direction in ["left", "right"]:
# For horizontal concat, pad heights to match
@@ -316,11 +329,11 @@ Optional spacing can be added between images.
if h1 < target_h:
pad_h = target_h - h1
pad_top, pad_bottom = pad_h // 2, pad_h - pad_h // 2
image1 = torch.nn.functional.pad(image1, (0, 0, 0, 0, pad_top, pad_bottom), mode='constant', value=0.0)
image1 = torch.nn.functional.pad(image1, (0, 0, 0, 0, pad_top, pad_bottom), mode='constant', value=pad_value)
if h2 < target_h:
pad_h = target_h - h2
pad_top, pad_bottom = pad_h // 2, pad_h - pad_h // 2
image2 = torch.nn.functional.pad(image2, (0, 0, 0, 0, pad_top, pad_bottom), mode='constant', value=0.0)
image2 = torch.nn.functional.pad(image2, (0, 0, 0, 0, pad_top, pad_bottom), mode='constant', value=pad_value)
else: # up, down
# For vertical concat, pad widths to match
if w1 != w2:
@@ -328,11 +341,11 @@ Optional spacing can be added between images.
if w1 < target_w:
pad_w = target_w - w1
pad_left, pad_right = pad_w // 2, pad_w - pad_w // 2
image1 = torch.nn.functional.pad(image1, (0, 0, pad_left, pad_right), mode='constant', value=0.0)
image1 = torch.nn.functional.pad(image1, (0, 0, pad_left, pad_right), mode='constant', value=pad_value)
if w2 < target_w:
pad_w = target_w - w2
pad_left, pad_right = pad_w // 2, pad_w - pad_w // 2
image2 = torch.nn.functional.pad(image2, (0, 0, pad_left, pad_right), mode='constant', value=0.0)
image2 = torch.nn.functional.pad(image2, (0, 0, pad_left, pad_right), mode='constant', value=pad_value)
# Ensure same number of channels
if image1.shape[-1] != image2.shape[-1]:
@@ -366,15 +379,6 @@ Optional spacing can be added between images.
if spacing_width > 0:
spacing_width = spacing_width + (spacing_width % 2) # Ensure even
color_map = {
"white": 1.0,
"black": 0.0,
"red": (1.0, 0.0, 0.0),
"green": (0.0, 1.0, 0.0),
"blue": (0.0, 0.0, 1.0),
}
color_val = color_map[spacing_color]
if direction in ["left", "right"]:
spacing_shape = (
image1.shape[0],
@@ -410,6 +414,62 @@ Optional spacing can be added between images.
concat_dim = 2 if direction in ["left", "right"] else 1
return (torch.cat(images, dim=concat_dim),)
class ResizeAndPadImage:
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"image": ("IMAGE",),
"target_width": ("INT", {
"default": 512,
"min": 1,
"max": MAX_RESOLUTION,
"step": 1
}),
"target_height": ("INT", {
"default": 512,
"min": 1,
"max": MAX_RESOLUTION,
"step": 1
}),
"padding_color": (["white", "black"],),
"interpolation": (["area", "bicubic", "nearest-exact", "bilinear", "lanczos"],),
}
}
RETURN_TYPES = ("IMAGE",)
FUNCTION = "resize_and_pad"
CATEGORY = "image/transform"
def resize_and_pad(self, image, target_width, target_height, padding_color, interpolation):
batch_size, orig_height, orig_width, channels = image.shape
scale_w = target_width / orig_width
scale_h = target_height / orig_height
scale = min(scale_w, scale_h)
new_width = int(orig_width * scale)
new_height = int(orig_height * scale)
image_permuted = image.permute(0, 3, 1, 2)
resized = comfy.utils.common_upscale(image_permuted, new_width, new_height, interpolation, "disabled")
pad_value = 0.0 if padding_color == "black" else 1.0
padded = torch.full(
(batch_size, channels, target_height, target_width),
pad_value,
dtype=image.dtype,
device=image.device
)
y_offset = (target_height - new_height) // 2
x_offset = (target_width - new_width) // 2
padded[:, :, y_offset:y_offset + new_height, x_offset:x_offset + new_width] = resized
output = padded.permute(0, 2, 3, 1)
return (output,)
class SaveSVGNode:
"""
@@ -532,5 +592,6 @@ NODE_CLASS_MAPPINGS = {
"SaveAnimatedPNG": SaveAnimatedPNG,
"SaveSVGNode": SaveSVGNode,
"ImageStitch": ImageStitch,
"ResizeAndPadImage": ResizeAndPadImage,
"GetImageSize": GetImageSize,
}

View File

@@ -268,6 +268,52 @@ class ModelMergeWAN2_1(comfy_extras.nodes_model_merging.ModelMergeBlocks):
return {"required": arg_dict}
class ModelMergeCosmosPredict2_2B(comfy_extras.nodes_model_merging.ModelMergeBlocks):
CATEGORY = "advanced/model_merging/model_specific"
@classmethod
def INPUT_TYPES(s):
arg_dict = { "model1": ("MODEL",),
"model2": ("MODEL",)}
argument = ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01})
arg_dict["pos_embedder."] = argument
arg_dict["x_embedder."] = argument
arg_dict["t_embedder."] = argument
arg_dict["t_embedding_norm."] = argument
for i in range(28):
arg_dict["blocks.{}.".format(i)] = argument
arg_dict["final_layer."] = argument
return {"required": arg_dict}
class ModelMergeCosmosPredict2_14B(comfy_extras.nodes_model_merging.ModelMergeBlocks):
CATEGORY = "advanced/model_merging/model_specific"
@classmethod
def INPUT_TYPES(s):
arg_dict = { "model1": ("MODEL",),
"model2": ("MODEL",)}
argument = ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01})
arg_dict["pos_embedder."] = argument
arg_dict["x_embedder."] = argument
arg_dict["t_embedder."] = argument
arg_dict["t_embedding_norm."] = argument
for i in range(36):
arg_dict["blocks.{}.".format(i)] = argument
arg_dict["final_layer."] = argument
return {"required": arg_dict}
NODE_CLASS_MAPPINGS = {
"ModelMergeSD1": ModelMergeSD1,
"ModelMergeSD2": ModelMergeSD1, #SD1 and SD2 have the same blocks
@@ -281,4 +327,6 @@ NODE_CLASS_MAPPINGS = {
"ModelMergeCosmos7B": ModelMergeCosmos7B,
"ModelMergeCosmos14B": ModelMergeCosmos14B,
"ModelMergeWAN2_1": ModelMergeWAN2_1,
"ModelMergeCosmosPredict2_2B": ModelMergeCosmosPredict2_2B,
"ModelMergeCosmosPredict2_14B": ModelMergeCosmosPredict2_14B,
}