wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-18 12:28:17 +08:00
Code Issues Actions 30 Packages Projects Releases Wiki Activity

Merge branch 'master' into fix/3d-advanced-api-mode

Browse Source
This commit is contained in:
Alexis Rolland 2026-07-14 09:51:53 +08:00 committed by GitHub
commit 0ba1243492
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 63 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
comfy/ldm/hidream_o1/attention.py
View File

@ -15,24 +15,24 @@ def make_two_pass_attention(ar_len: int, transformer_options=None):
The AR pass goes through SDPA directand bypasses wrappers, it is only ~1% of T at typical edit sizes.
"""
def two_pass_attention(q, k, v, heads, **kwargs):
def two_pass_attention(q, k, v, heads, enable_gqa=False, **kwargs):
B, H, T, D = q.shape
if T < k.shape[2]: # KV-cache hot path: Q is shorter than K/V (cached AR prefix is in K/V only), all fresh Q positions are in the gen region, single full-attention call
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options)
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options, enable_gqa=enable_gqa)
elif ar_len >= T:
out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True)
out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True, enable_gqa=enable_gqa)
elif ar_len <= 0:
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options)
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options, enable_gqa=enable_gqa)
else:
out_ar = comfy.ops.scaled_dot_product_attention(
q[:, :, :ar_len], k[:, :, :ar_len], v[:, :, :ar_len],
attn_mask=None, dropout_p=0.0, is_causal=True,
attn_mask=None, dropout_p=0.0, is_causal=True, enable_gqa=enable_gqa,
)
out_gen = optimized_attention(
q[:, :, ar_len:], k, v, heads,
mask=None, skip_reshape=True, skip_output_reshape=True,
transformer_options=transformer_options,
transformer_options=transformer_options, enable_gqa=enable_gqa,
)
out = torch.cat([out_ar, out_gen], dim=2)

6
comfy_api_nodes/nodes_gemini.py
View File

@ -1133,7 +1133,9 @@ class GeminiImage2(IO.ComfyNode):
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
if model == "Nano Banana 2 (Gemini 3.1 Flash Image)":
model = "gemini-3.1-flash-image-preview"
model = "gemini-3.1-flash-image"
elif model == "gemini-3-pro-image-preview":
model = "gemini-3-pro-image"
parts: list[GeminiPart] = [GeminiPart(text=prompt)]
if images is not None:
@ -1507,7 +1509,7 @@ class GeminiNanoBanana2V2(IO.ComfyNode):
validate_string(prompt, strip_whitespace=True, min_length=1)
model_choice = model["model"]
if model_choice == "Nano Banana 2 (Gemini 3.1 Flash Image)":
model_id = "gemini-3.1-flash-image-preview"
model_id = "gemini-3.1-flash-image"
elif model_choice == "Nano Banana 2 Lite":
model_id = "gemini-3.1-flash-lite-image"
else:

2
comfy_api_nodes/util/_helpers.py
View File

@ -15,6 +15,7 @@ from comfy.comfy_api_env import normalize_comfy_api_base
from comfy.deploy_environment import get_deploy_environment
from comfy.model_management import processing_interrupted
from comfy_api.latest import IO
from comfyui_version import __version__ as comfyui_version
from .common_exceptions import ProcessingInterrupted
@ -60,6 +61,7 @@ def get_comfy_api_headers(node_cls: type[IO.ComfyNode]) -> dict[str, str]:
**get_auth_header(node_cls),
"Comfy-Env": get_deploy_environment(),
"Comfy-Usage-Source": get_usage_source(node_cls),
"Comfy-Core-Version": comfyui_version,
}

37
comfy_extras/nodes_images.py
View File

@ -844,15 +844,18 @@ class ImageMergeTileList(IO.ComfyNode):
# Format specifications
# ---------------------------------------------------------------------------
# Maps (file_format, bit_depth, has_alpha) -> (numpy dtype scale, av pixel format,
# stream pix_fmt). Keeps the encode path declarative instead of branchy.
# Maps (file_format, bit_depth, num_channels) -> (quantization scale, numpy dtype,
# av frame pix_fmt, stream pix_fmt). Keeps the encode path declarative instead of branchy.
_FORMAT_SPECS = {
("png", "8-bit", False): {"scale": 255.0, "dtype": np.uint8, "frame_fmt": "rgb24", "stream_fmt": "rgb24"},
("png", "8-bit", True): {"scale": 255.0, "dtype": np.uint8, "frame_fmt": "rgba", "stream_fmt": "rgba"},
("png", "16-bit", False): {"scale": 65535.0, "dtype": np.uint16, "frame_fmt": "rgb48le", "stream_fmt": "rgb48be"},
("png", "16-bit", True): {"scale": 65535.0, "dtype": np.uint16, "frame_fmt": "rgba64le", "stream_fmt": "rgba64be"},
("exr", "32-bit float", False): {"scale": 1.0, "dtype": np.float32, "frame_fmt": "gbrpf32le", "stream_fmt": "gbrpf32le"},
("exr", "32-bit float", True): {"scale": 1.0, "dtype": np.float32, "frame_fmt": "gbrapf32le", "stream_fmt": "gbrapf32le"},
("png", "8-bit", 1): {"scale": 255.0, "dtype": np.uint8, "frame_fmt": "gray", "stream_fmt": "gray"},
("png", "8-bit", 3): {"scale": 255.0, "dtype": np.uint8, "frame_fmt": "rgb24", "stream_fmt": "rgb24"},
("png", "8-bit", 4): {"scale": 255.0, "dtype": np.uint8, "frame_fmt": "rgba", "stream_fmt": "rgba"},
("png", "16-bit", 1): {"scale": 65535.0, "dtype": np.uint16, "frame_fmt": "gray16le", "stream_fmt": "gray16be"},
("png", "16-bit", 3): {"scale": 65535.0, "dtype": np.uint16, "frame_fmt": "rgb48le", "stream_fmt": "rgb48be"},
("png", "16-bit", 4): {"scale": 65535.0, "dtype": np.uint16, "frame_fmt": "rgba64le", "stream_fmt": "rgba64be"},
("exr", "32-bit float", 1): {"scale": 1.0, "dtype": np.float32, "frame_fmt": "grayf32le", "stream_fmt": "grayf32le"},
("exr", "32-bit float", 3): {"scale": 1.0, "dtype": np.float32, "frame_fmt": "gbrpf32le", "stream_fmt": "gbrpf32le"},
("exr", "32-bit float", 4): {"scale": 1.0, "dtype": np.float32, "frame_fmt": "gbrapf32le", "stream_fmt": "gbrapf32le"},
}
@ -891,10 +894,11 @@ def hlg_to_linear(t: torch.Tensor) -> torch.Tensor:
return torch.cat([hlg_to_linear(rgb), alpha], dim=-1)
# Piecewise: sqrt branch below 0.5, log branch above.
# Clamp inside the log branch so negative / out-of-range values don't blow up;
# Clamp the log branch at the 0.5 branch point (not above it) so the
# unselected lane stays finite in exp() without altering selected values;
# values above 1.0 are allowed and extrapolate naturally.
low = (t ** 2) / 3.0
high = (torch.exp((t.clamp(min=_HLG_C) - _HLG_C) / _HLG_A) + _HLG_B) / 12.0
high = (torch.exp((t.clamp(min=0.5) - _HLG_C) / _HLG_A) + _HLG_B) / 12.0
return torch.where(t <= 0.5, low, high)
@ -1087,7 +1091,8 @@ def _encode_image(
bit_depth: str,
colorspace: str,
) -> bytes:
"""Encode a single HxWxC tensor to PNG or EXR bytes in memory.
"""Encode a single HxWxC (or channel-less HxW grayscale) tensor to PNG or
EXR bytes in memory. Grayscale is written as single-channel PNG / Y-only EXR.
For EXR the input is interpreted according to `colorspace` and converted
to scene-linear (EXR's convention) before writing:
@ -1101,10 +1106,16 @@ def _encode_image(
For PNG, colorspace selection does not modify pixels — PNG is delivered
sRGB-encoded and there is no PNG path for wide-gamut HDR in this node.
"""
if img_tensor.ndim == 2:
img_tensor = img_tensor.unsqueeze(-1) # Some nodes emit grayscale as (H, W) with no channel dim, mask-style.
height, width, num_channels = img_tensor.shape
has_alpha = num_channels == 4
spec = _FORMAT_SPECS[(file_format, bit_depth, has_alpha)]
spec = _FORMAT_SPECS.get((file_format, bit_depth, num_channels))
if spec is None:
raise ValueError(
f"No {file_format}/{bit_depth} encoder for {num_channels}-channel images: "
"supported channel counts are 1 (grayscale), 3 (RGB) and 4 (RGBA)."
)
if spec["dtype"] == np.float32:
# EXR path: preserve full range, no clamp.

45
openapi.yaml
View File

@ -7,18 +7,18 @@ components:
description: Timestamp when the asset was created
format: date-time
type: string
display_name:
description: Display name of the asset. Mirrors name for backwards compatibility.
nullable: true
type: string
file_path:
description: Relative path in global-namespace-root form (e.g. "models/checkpoints/flux.safetensors")
nullable: true
type: string
hash:
description: Blake3 hash of the asset content.
pattern: ^blake3:[a-f0-9]{64}$
type: string
loader_path:
description: The value a loader consumes to load this asset. Null when no loader can resolve the file.
nullable: true
type: string
display_name:
description: Human-facing label for the asset. Not unique.
nullable: true
type: string
id:
description: Unique identifier for the asset
format: uuid
@ -144,6 +144,14 @@ components:
AssetUpdated:
description: Response returned when an existing asset is successfully updated.
properties:
display_name:
description: Display name of the asset. Mirrors name for backwards compatibility.
nullable: true
type: string
file_path:
description: Relative path in global-namespace-root form (e.g. "models/checkpoints/flux.safetensors")
nullable: true
type: string
hash:
description: Blake3 hash of the asset content.
pattern: ^blake3:[a-f0-9]{64}$
@ -775,14 +783,6 @@ components:
ModelFolder:
description: Represents a folder containing models
properties:
extensions:
description: The folder's registered file-extension allowlist. An empty array means the folder accepts any extension (match-all).
example:
- .ckpt
- .safetensors
items:
type: string
type: array
folders:
description: List of paths where models of this type are stored
example:
@ -1644,7 +1644,7 @@ paths:
format: uuid
type: string
tags:
description: JSON-encoded array of tag strings. For new byte uploads, include exactly one destination role (`input`, `output`, or `models`); `models` uploads also require exactly one `model_type:<folder_name>` tag. Extra tags are stored as labels and do not create path components.
description: JSON-encoded array of freeform tag strings, e.g. '["models","checkpoint"]'. Common types include "models", "input", "output", and "temp", but any tag can be used in any order.
type: string
user_metadata:
description: Custom JSON metadata as a string
@ -1829,7 +1829,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/Asset'
$ref: '#/components/schemas/AssetUpdated'
description: Asset updated successfully
"400":
content:
@ -2470,9 +2470,6 @@ paths:
supports_preview_metadata:
description: Whether the server supports preview metadata
type: boolean
supports_model_type_tags:
description: Whether the server supports namespaced model type asset tags
type: boolean
type: object
description: Success
headers:
@ -3300,6 +3297,12 @@ paths:
schema:
$ref: '#/components/schemas/ErrorResponse'
description: Invalid request parameters
"401":
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
description: Unauthorized - Authentication required
"500":
content:
application/json:

6
requirements.txt
View File

@ -1,6 +1,6 @@
comfyui-frontend-package==1.45.20
comfyui-workflow-templates==0.11.6
comfyui-embedded-docs==0.5.7
comfyui-workflow-templates==0.11.9
comfyui-embedded-docs==0.5.8
torch
torchsde
torchvision
@ -22,7 +22,7 @@ alembic
SQLAlchemy>=2.0.0
filelock
av>=16.0.0
comfy-kitchen==0.2.18
comfy-kitchen==0.2.19
comfy-aimdo==0.4.10
requests
simpleeval>=1.0.0