wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-03 21:20:49 +08:00
Code Issues Actions 22 Packages Projects Releases Wiki Activity

Merge branch 'master' into sam3d_body

Browse Source
This commit is contained in:
comfyanonymous 2026-07-02 17:56:28 -07:00 committed by GitHub
commit 2175db9ada
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 107 additions and 453 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
AGENTS.md
View File

@ -8,10 +8,13 @@
directly required. directly required.
- Prefer practical fixes over broad architecture work. Add abstractions only - Prefer practical fixes over broad architecture work. Add abstractions only
when they remove real repeated logic or match an existing ComfyUI pattern. when they remove real repeated logic or match an existing ComfyUI pattern.
- Prefer fewer dependencies. Do not add new dependencies to ComfyUI unless they
are absolutely necessary.
- Delete obsolete code aggressively when newer infrastructure makes it useless. - Delete obsolete code aggressively when newer infrastructure makes it useless.
Remove dead fallbacks, migration paths, unused options, debug prints, and Remove dead fallbacks, migration paths, unused options, debug prints, and
compatibility branches that are no longer needed. Do not leave dead branches, compatibility branches that are no longer needed. Do not leave dead branches,
unreachable code, or functions that are never called. unreachable code, or functions that are never called. If code is not
necessary for the current behavior, remove it.
- Revert or disable problematic behavior quickly when it breaks users. It is - Revert or disable problematic behavior quickly when it breaks users. It is
better to remove a broken feature path than keep a complicated partial fix. better to remove a broken feature path than keep a complicated partial fix.
- Preserve existing APIs, node names, model-loading behavior, file layout, and - Preserve existing APIs, node names, model-loading behavior, file layout, and
@ -85,6 +88,14 @@
not change a shared method to return extra values, alternate shapes, or not change a shared method to return extra values, alternate shapes, or
sentinel wrappers for one implementation unless the shared interface is sentinel wrappers for one implementation unless the shared interface is
explicitly updated. explicitly updated.
- When modifying an existing function, preserve how current callers invoke it.
Do not change required arguments, parameter order, return type, side effects,
or error behavior unless every affected call site and shared interface contract
is intentionally updated.
- Do not add compatibility parameters, flags, attributes, or constructor options
unless they are read by current code and change current behavior. Remove
pass-through or stored-but-unused values instead of preserving upstream or
deprecated API baggage.
- If an implementation needs auxiliary values for its own workflow, expose them - If an implementation needs auxiliary values for its own workflow, expose them
through a private helper or a clearly named implementation-specific method through a private helper or a clearly named implementation-specific method
instead of overloading the public method's return contract. instead of overloading the public method's return contract.
@ -102,6 +113,11 @@
- Do not add freeze, unfreeze, or trainability toggles to model classes. ComfyUI - Do not add freeze, unfreeze, or trainability toggles to model classes. ComfyUI
models are always treated as frozen for inference, so explicit freeze models are always treated as frozen for inference, so explicit freeze
functionality is redundant and should not be added. functionality is redundant and should not be added.
- Remove training-only behavior such as dropout from inference model code, but
preserve checkpoint and state-dict compatibility when doing so. If deleting a
module would change state-dict keys, module ordering, or checkpoint loading
behavior, replace it with a no-op such as `nn.Identity` instead of removing the
slot outright.
## Python Style ## Python Style
@ -111,6 +127,11 @@
- Do not add unnecessary `try`/`except` blocks. Use them for optional dependency, - Do not add unnecessary `try`/`except` blocks. Use them for optional dependency,
platform, or backend capability detection only when the program has a useful platform, or backend capability detection only when the program has a useful
fallback. Prefer specific exception types when changing new code. fallback. Prefer specific exception types when changing new code.
- 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
comment naming the exact PyTorch version or versions that still need it,
remove it.
- Let unsupported model formats, invalid quantization metadata, and bad states - Let unsupported model formats, invalid quantization metadata, and bad states
fail with clear errors instead of silently producing lower quality output. fail with clear errors instead of silently producing lower quality output.
- Match the existing local style in the file you edit. This codebase tolerates - Match the existing local style in the file you edit. This codebase tolerates
@ -129,8 +150,87 @@
adding parallel code paths. Use `comfy.quant_ops`, `comfy.model_management`, adding parallel code paths. Use `comfy.quant_ops`, `comfy.model_management`,
`comfy.memory_management`, `comfy.pinned_memory`, `comfy_aimdo`, and `comfy.memory_management`, `comfy.pinned_memory`, `comfy_aimdo`, and
`comfy-kitchen` helpers where they already solve the problem. `comfy-kitchen` helpers where they already solve the problem.
- Use optimized comfy-kitchen ops in places where they improve performance
without changing the expected dtype, device, memory, or interface behavior.
- All models should use the optimized attention function selected by ComfyUI.
Treat optimized backend functions, dispatch helpers, and capability-selected
callables as opaque. Higher-level code must not inspect function identity,
names, modules, or implementation details to decide behavior.
- Apply the same opacity rule to similar patterns beyond attention: callers
should depend on the documented interface and result contract, not on which
backend implementation was selected underneath.
- Do not use custom inference ops that only duplicate an existing op while
upcasting to float32, such as custom RMSNorm variants. Use the generic ComfyUI
ops and/or native torch ops instead.
- If a model class `__init__` has an `operations` parameter, assume
`operations` is never `None`. Do not add fallback branches or default torch
ops for a missing `operations` object.
- Do not add unnecessary parameters to model, model block, or model ops related
classes. Constructor and forward signatures should carry only values that are
actually needed by that object for inference.
- Reuse existing model classes, blocks, ops, and helper modules when appropriate.
Before implementing a new version of a model component, search the existing
model code for a class or helper that already provides the behavior.
- Avoid adding `einops` usage in core inference code. Use native torch tensor
ops such as `reshape`, `view`, `permute`, `transpose`, `flatten`, `unflatten`,
`unsqueeze`, and `squeeze` instead.
- Do not use tensors as general-purpose Python data structures. Keep metadata,
bookkeeping, counters, flags, shape math, padding math, index planning, memory
estimates, and control-flow decisions in plain Python values unless the data
must participate directly in tensor computation. Avoid creating temporary
tensors just to use tensor methods for scalar or structural calculations.
- Avoid unnecessary casts and transfers. Preserve the intended compute dtype, - Avoid unnecessary casts and transfers. Preserve the intended compute dtype,
storage dtype, bias dtype, and original tensor shape metadata. storage dtype, bias dtype, and original tensor shape metadata.
- Assume inputs to the main model forward are already in the compute dtype by
default, except integer inputs such as some model timestep tensors. Do not add
defensive or convenience casts in model code; it is better for invalid dtype
plumbing to error clearly than to hide it with unnecessary casts.
- Raw model parameters that are not owned by an op and may be initialized in a
dtype different from the compute dtype should be cast at use in forward or
inference code with `comfy.ops.cast_to_input` or
`comfy.model_management.cast_to` to avoid dtype mismatches.
- Model code should not care what dtype it is initialized in, and model
`__init__` methods should not contain workarounds for specific dtypes. Dtype
workaround code, such as making a model work with fp16 compute, belongs in the
execution or model-management layer that owns compute policy.
- Model code should not perform unnecessary device-to-CPU or CPU-to-device
transfers. New allocations must be created on the correct device and dtype;
never allocate on CPU and then move to GPU, or allocate in one dtype and then
convert to another.
- Model code itself should not perform memory management. Loading, unloading,
offloading, device movement, VRAM policy, cache lifetime, and cleanup belong
in the relevant model-management and execution layers, not inside model
implementations.
- Do not add global, module-level, class-level, singleton, or model-owned stores
for tensors or other large memory that persist across executions. Temporary
caches must be scoped to a single execution or forward/encode/decode call:
allocate them in the owning top-level call, pass them explicitly through the
call stack, and let them be discarded when that call returns.
- Follow the Wan VAE temporal cache pattern for temporary caches: create a local
cache such as `feat_map` for the encode/decode operation, pass it into the
blocks that need it, and do not retain it on the model or in global state.
- In model init code, prefer `torch.empty` for parameter/buffer placeholders
that are populated from the model state dict instead of zero-initializing with
`torch.zeros` or similar. If an allocation is not loaded from the state dict
and is useless for inference, do not include it.
- `nn.Parameter` tensors that are stored in and populated from the model state
dict should be initialized with `torch.empty`, not with zero, random, or
otherwise meaningful initialization.
- Model initialization should describe module structure, not fabricate
checkpoint-owned tensor contents. Parameters and buffers that are loaded from
the state dict must not be manually initialized, reassigned, or filled with
fallback values unless that value is actually used when no checkpoint key
exists.
- When slicing large tensors, copy the slice if the sliced tensor's lifetime
exceeds the current function scope. Do not keep a long-lived view into a large
backing tensor when a smaller copy would release memory sooner.
- Use fused or compound torch operations such as `addcmul` when they naturally
match the math. Reducing Python and torch dispatch overhead is a valid
optimization when it does not obscure the code or change dtype/device
behavior.
- Avoid caches that persist across different executions as much as possible.
Persistent caches are acceptable only when they use a very minimal amount of
memory and have a clear ownership and invalidation story.
- When optimizing, favor small measurable changes: fewer allocations, fewer - When optimizing, favor small measurable changes: fewer allocations, fewer
device transfers, less peak memory, better batching, or use of a faster device transfers, less peak memory, better batching, or use of a faster
existing backend op. existing backend op.
@ -141,6 +241,12 @@
`CATEGORY`, and registration through the local mapping used by that file. `CATEGORY`, and registration through the local mapping used by that file.
- Keep node changes backward compatible by default. Add inputs with sensible - Keep node changes backward compatible by default. Add inputs with sensible
defaults and avoid changing output types unless the request requires it. defaults and avoid changing output types unless the request requires it.
- Model implementations should add the minimal number of ComfyUI nodes required
to run the model. Reuse existing nodes as much as possible; adapting the model
to work with existing nodes is strongly preferred over creating new nodes.
- Node-level code must not patch model code directly. Any node behavior that
modifies, wraps, hooks, or changes model behavior must go through the model
patcher class instead of reaching into model internals.
- The official mascot of ComfyUI is a very cute anime girl with massive fennec - The official mascot of ComfyUI is a very cute anime girl with massive fennec
ears, a big fluffy tail, long blonde wavy hair, and blue eyes. Feel free to ears, a big fluffy tail, long blonde wavy hair, and blue eyes. Feel free to
use her in ComfyUI materials, UI text, examples, tests, generated assets, or use her in ComfyUI materials, UI text, examples, tests, generated assets, or

61
comfy_api_nodes/apis/ideogram.py
View File

@ -33,53 +33,6 @@ class IdeogramColorPalette(
) )
class ImageRequest(BaseModel):
aspect_ratio: Optional[str] = Field(
None,
description="Optional. The aspect ratio (e.g., 'ASPECT_16_9', 'ASPECT_1_1'). Cannot be used with resolution. Defaults to 'ASPECT_1_1' if unspecified.",
)
color_palette: Optional[Dict[str, Any]] = Field(
None, description='Optional. Color palette object. Only for V_2, V_2_TURBO.'
)
magic_prompt_option: Optional[str] = Field(
None, description="Optional. MagicPrompt usage ('AUTO', 'ON', 'OFF')."
)
model: str = Field(..., description="The model used (e.g., 'V_2', 'V_2A_TURBO')")
negative_prompt: Optional[str] = Field(
None,
description='Optional. Description of what to exclude. Only for V_1, V_1_TURBO, V_2, V_2_TURBO.',
)
num_images: Optional[int] = Field(
1,
description='Optional. Number of images to generate (1-8). Defaults to 1.',
ge=1,
le=8,
)
prompt: str = Field(
..., description='Required. The prompt to use to generate the image.'
)
resolution: Optional[str] = Field(
None,
description="Optional. Resolution (e.g., 'RESOLUTION_1024_1024'). Only for model V_2. Cannot be used with aspect_ratio.",
)
seed: Optional[int] = Field(
None,
description='Optional. A number between 0 and 2147483647.',
ge=0,
le=2147483647,
)
style_type: Optional[str] = Field(
None,
description="Optional. Style type ('AUTO', 'GENERAL', 'REALISTIC', 'DESIGN', 'RENDER_3D', 'ANIME'). Only for models V_2 and above.",
)
class IdeogramGenerateRequest(BaseModel):
image_request: ImageRequest = Field(
..., description='The image generation request parameters.'
)
class Datum(BaseModel): class Datum(BaseModel):
is_image_safe: Optional[bool] = Field( is_image_safe: Optional[bool] = Field(
None, description='Indicates whether the image is considered safe.' None, description='Indicates whether the image is considered safe.'
@ -113,20 +66,6 @@ class StyleCode(RootModel[str]):
root: str = Field(..., pattern='^[0-9A-Fa-f]{8}$') root: str = Field(..., pattern='^[0-9A-Fa-f]{8}$')
class Datum1(BaseModel):
is_image_safe: Optional[bool] = None
prompt: Optional[str] = None
resolution: Optional[str] = None
seed: Optional[int] = None
style_type: Optional[str] = None
url: Optional[str] = None
class IdeogramV3IdeogramResponse(BaseModel):
created: Optional[datetime] = None
data: Optional[List[Datum1]] = None
class RenderingSpeed1(str, Enum): class RenderingSpeed1(str, Enum):
TURBO = 'TURBO' TURBO = 'TURBO'
DEFAULT = 'DEFAULT' DEFAULT = 'DEFAULT'

391
comfy_api_nodes/nodes_ideogram.py
View File

@ -5,9 +5,7 @@ from PIL import Image
import numpy as np import numpy as np
import torch import torch
from comfy_api_nodes.apis.ideogram import ( from comfy_api_nodes.apis.ideogram import (
IdeogramGenerateRequest,
IdeogramGenerateResponse, IdeogramGenerateResponse,
ImageRequest,
IdeogramV3Request, IdeogramV3Request,
IdeogramV3EditRequest, IdeogramV3EditRequest,
IdeogramV4Request, IdeogramV4Request,
@ -21,101 +19,6 @@ from comfy_api_nodes.util import (
validate_string, validate_string,
) )
V1_V1_RES_MAP = {
"Auto":"AUTO",
"512 x 1536":"RESOLUTION_512_1536",
"576 x 1408":"RESOLUTION_576_1408",
"576 x 1472":"RESOLUTION_576_1472",
"576 x 1536":"RESOLUTION_576_1536",
"640 x 1024":"RESOLUTION_640_1024",
"640 x 1344":"RESOLUTION_640_1344",
"640 x 1408":"RESOLUTION_640_1408",
"640 x 1472":"RESOLUTION_640_1472",
"640 x 1536":"RESOLUTION_640_1536",
"704 x 1152":"RESOLUTION_704_1152",
"704 x 1216":"RESOLUTION_704_1216",
"704 x 1280":"RESOLUTION_704_1280",
"704 x 1344":"RESOLUTION_704_1344",
"704 x 1408":"RESOLUTION_704_1408",
"704 x 1472":"RESOLUTION_704_1472",
"720 x 1280":"RESOLUTION_720_1280",
"736 x 1312":"RESOLUTION_736_1312",
"768 x 1024":"RESOLUTION_768_1024",
"768 x 1088":"RESOLUTION_768_1088",
"768 x 1152":"RESOLUTION_768_1152",
"768 x 1216":"RESOLUTION_768_1216",
"768 x 1232":"RESOLUTION_768_1232",
"768 x 1280":"RESOLUTION_768_1280",
"768 x 1344":"RESOLUTION_768_1344",
"832 x 960":"RESOLUTION_832_960",
"832 x 1024":"RESOLUTION_832_1024",
"832 x 1088":"RESOLUTION_832_1088",
"832 x 1152":"RESOLUTION_832_1152",
"832 x 1216":"RESOLUTION_832_1216",
"832 x 1248":"RESOLUTION_832_1248",
"864 x 1152":"RESOLUTION_864_1152",
"896 x 960":"RESOLUTION_896_960",
"896 x 1024":"RESOLUTION_896_1024",
"896 x 1088":"RESOLUTION_896_1088",
"896 x 1120":"RESOLUTION_896_1120",
"896 x 1152":"RESOLUTION_896_1152",
"960 x 832":"RESOLUTION_960_832",
"960 x 896":"RESOLUTION_960_896",
"960 x 1024":"RESOLUTION_960_1024",
"960 x 1088":"RESOLUTION_960_1088",
"1024 x 640":"RESOLUTION_1024_640",
"1024 x 768":"RESOLUTION_1024_768",
"1024 x 832":"RESOLUTION_1024_832",
"1024 x 896":"RESOLUTION_1024_896",
"1024 x 960":"RESOLUTION_1024_960",
"1024 x 1024":"RESOLUTION_1024_1024",
"1088 x 768":"RESOLUTION_1088_768",
"1088 x 832":"RESOLUTION_1088_832",
"1088 x 896":"RESOLUTION_1088_896",
"1088 x 960":"RESOLUTION_1088_960",
"1120 x 896":"RESOLUTION_1120_896",
"1152 x 704":"RESOLUTION_1152_704",
"1152 x 768":"RESOLUTION_1152_768",
"1152 x 832":"RESOLUTION_1152_832",
"1152 x 864":"RESOLUTION_1152_864",
"1152 x 896":"RESOLUTION_1152_896",
"1216 x 704":"RESOLUTION_1216_704",
"1216 x 768":"RESOLUTION_1216_768",
"1216 x 832":"RESOLUTION_1216_832",
"1232 x 768":"RESOLUTION_1232_768",
"1248 x 832":"RESOLUTION_1248_832",
"1280 x 704":"RESOLUTION_1280_704",
"1280 x 720":"RESOLUTION_1280_720",
"1280 x 768":"RESOLUTION_1280_768",
"1280 x 800":"RESOLUTION_1280_800",
"1312 x 736":"RESOLUTION_1312_736",
"1344 x 640":"RESOLUTION_1344_640",
"1344 x 704":"RESOLUTION_1344_704",
"1344 x 768":"RESOLUTION_1344_768",
"1408 x 576":"RESOLUTION_1408_576",
"1408 x 640":"RESOLUTION_1408_640",
"1408 x 704":"RESOLUTION_1408_704",
"1472 x 576":"RESOLUTION_1472_576",
"1472 x 640":"RESOLUTION_1472_640",
"1472 x 704":"RESOLUTION_1472_704",
"1536 x 512":"RESOLUTION_1536_512",
"1536 x 576":"RESOLUTION_1536_576",
"1536 x 640":"RESOLUTION_1536_640",
}
V1_V2_RATIO_MAP = {
"1:1":"ASPECT_1_1",
"4:3":"ASPECT_4_3",
"3:4":"ASPECT_3_4",
"16:9":"ASPECT_16_9",
"9:16":"ASPECT_9_16",
"2:1":"ASPECT_2_1",
"1:2":"ASPECT_1_2",
"3:2":"ASPECT_3_2",
"2:3":"ASPECT_2_3",
"4:5":"ASPECT_4_5",
"5:4":"ASPECT_5_4",
}
V3_RATIO_MAP = { V3_RATIO_MAP = {
"1:3":"1x3", "1:3":"1x3",
@ -229,298 +132,6 @@ async def download_and_process_images(image_urls):
return stacked_tensors return stacked_tensors
class IdeogramV1(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="IdeogramV1",
display_name="Ideogram V1",
category="partner/image/Ideogram",
description="Generates images using the Ideogram V1 model.",
inputs=[
IO.String.Input(
"prompt",
multiline=True,
default="",
tooltip="Prompt for the image generation",
),
IO.Boolean.Input(
"turbo",
default=False,
tooltip="Whether to use turbo mode (faster generation, potentially lower quality)",
),
IO.Combo.Input(
"aspect_ratio",
options=list(V1_V2_RATIO_MAP.keys()),
default="1:1",
tooltip="The aspect ratio for image generation.",
optional=True,
),
IO.Combo.Input(
"magic_prompt_option",
options=["AUTO", "ON", "OFF"],
default="AUTO",
tooltip="Determine if MagicPrompt should be used in generation",
optional=True,
advanced=True,
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
control_after_generate=True,
display_mode=IO.NumberDisplay.number,
optional=True,
),
IO.String.Input(
"negative_prompt",
multiline=True,
default="",
tooltip="Description of what to exclude from the image",
optional=True,
),
IO.Int.Input(
"num_images",
default=1,
min=1,
max=8,
step=1,
display_mode=IO.NumberDisplay.number,
optional=True,
),
],
outputs=[
IO.Image.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["num_images", "turbo"]),
expr="""
(
$n := widgets.num_images;
$base := (widgets.turbo = true) ? 0.0286 : 0.0858;
{"type":"usd","usd": $round($base * $n, 2)}
)
""",
),
)
@classmethod
async def execute(
cls,
prompt,
turbo=False,
aspect_ratio="1:1",
magic_prompt_option="AUTO",
seed=0,
negative_prompt="",
num_images=1,
):
# Determine the model based on turbo setting
aspect_ratio = V1_V2_RATIO_MAP.get(aspect_ratio, None)
model = "V_1_TURBO" if turbo else "V_1"
response = await sync_op(
cls,
ApiEndpoint(path="/proxy/ideogram/generate", method="POST"),
response_model=IdeogramGenerateResponse,
data=IdeogramGenerateRequest(
image_request=ImageRequest(
prompt=prompt,
model=model,
num_images=num_images,
seed=seed,
aspect_ratio=aspect_ratio if aspect_ratio != "ASPECT_1_1" else None,
magic_prompt_option=(magic_prompt_option if magic_prompt_option != "AUTO" else None),
negative_prompt=negative_prompt if negative_prompt else None,
)
),
max_retries=1,
)
if not response.data or len(response.data) == 0:
raise Exception("No images were generated in the response")
image_urls = [image_data.url for image_data in response.data if image_data.url]
if not image_urls:
raise Exception("No image URLs were generated in the response")
return IO.NodeOutput(await download_and_process_images(image_urls))
class IdeogramV2(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="IdeogramV2",
display_name="Ideogram V2",
category="partner/image/Ideogram",
description="Generates images using the Ideogram V2 model.",
inputs=[
IO.String.Input(
"prompt",
multiline=True,
default="",
tooltip="Prompt for the image generation",
),
IO.Boolean.Input(
"turbo",
default=False,
tooltip="Whether to use turbo mode (faster generation, potentially lower quality)",
),
IO.Combo.Input(
"aspect_ratio",
options=list(V1_V2_RATIO_MAP.keys()),
default="1:1",
tooltip="The aspect ratio for image generation. Ignored if resolution is not set to AUTO.",
optional=True,
),
IO.Combo.Input(
"resolution",
options=list(V1_V1_RES_MAP.keys()),
default="Auto",
tooltip="The resolution for image generation. "
"If not set to AUTO, this overrides the aspect_ratio setting.",
optional=True,
),
IO.Combo.Input(
"magic_prompt_option",
options=["AUTO", "ON", "OFF"],
default="AUTO",
tooltip="Determine if MagicPrompt should be used in generation",
optional=True,
advanced=True,
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
control_after_generate=True,
display_mode=IO.NumberDisplay.number,
optional=True,
),
IO.Combo.Input(
"style_type",
options=["AUTO", "GENERAL", "REALISTIC", "DESIGN", "RENDER_3D", "ANIME"],
default="NONE",
tooltip="Style type for generation (V2 only)",
optional=True,
advanced=True,
),
IO.String.Input(
"negative_prompt",
multiline=True,
default="",
tooltip="Description of what to exclude from the image",
optional=True,
),
IO.Int.Input(
"num_images",
default=1,
min=1,
max=8,
step=1,
display_mode=IO.NumberDisplay.number,
optional=True,
),
#"color_palette": (
# IO.STRING,
# {
# "multiline": False,
# "default": "",
# "tooltip": "Color palette preset name or hex colors with weights",
# },
#),
],
outputs=[
IO.Image.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["num_images", "turbo"]),
expr="""
(
$n := widgets.num_images;
$base := (widgets.turbo = true) ? 0.0715 : 0.1144;
{"type":"usd","usd": $round($base * $n, 2)}
)
""",
),
)
@classmethod
async def execute(
cls,
prompt,
turbo=False,
aspect_ratio="1:1",
resolution="Auto",
magic_prompt_option="AUTO",
seed=0,
style_type="NONE",
negative_prompt="",
num_images=1,
color_palette="",
):
aspect_ratio = V1_V2_RATIO_MAP.get(aspect_ratio, None)
resolution = V1_V1_RES_MAP.get(resolution, None)
# Determine the model based on turbo setting
model = "V_2_TURBO" if turbo else "V_2"
# Handle resolution vs aspect_ratio logic
# If resolution is not AUTO, it overrides aspect_ratio
final_resolution = None
final_aspect_ratio = None
if resolution != "AUTO":
final_resolution = resolution
else:
final_aspect_ratio = aspect_ratio if aspect_ratio != "ASPECT_1_1" else None
response = await sync_op(
cls,
endpoint=ApiEndpoint(path="/proxy/ideogram/generate", method="POST"),
response_model=IdeogramGenerateResponse,
data=IdeogramGenerateRequest(
image_request=ImageRequest(
prompt=prompt,
model=model,
num_images=num_images,
seed=seed,
aspect_ratio=final_aspect_ratio,
resolution=final_resolution,
magic_prompt_option=(magic_prompt_option if magic_prompt_option != "AUTO" else None),
style_type=style_type if style_type != "NONE" else None,
negative_prompt=negative_prompt if negative_prompt else None,
color_palette=color_palette if color_palette else None,
)
),
max_retries=1,
)
if not response.data or len(response.data) == 0:
raise Exception("No images were generated in the response")
image_urls = [image_data.url for image_data in response.data if image_data.url]
if not image_urls:
raise Exception("No image URLs were generated in the response")
return IO.NodeOutput(await download_and_process_images(image_urls))
class IdeogramV3(IO.ComfyNode): class IdeogramV3(IO.ComfyNode):
@classmethod @classmethod
@ -917,8 +528,6 @@ class IdeogramExtension(ComfyExtension):
@override @override
async def get_node_list(self) -> list[type[IO.ComfyNode]]: async def get_node_list(self) -> list[type[IO.ComfyNode]]:
return [ return [
IdeogramV1,
IdeogramV2,
IdeogramV3, IdeogramV3,
IdeogramV4, IdeogramV4,
] ]