diff --git a/comfy/k_diffusion/sampling.py b/comfy/k_diffusion/sampling.py index 753c66afa..1ba9edad7 100644 --- a/comfy/k_diffusion/sampling.py +++ b/comfy/k_diffusion/sampling.py @@ -1618,6 +1618,17 @@ def sample_seeds_2(model, x, sigmas, extra_args=None, callback=None, disable=Non x = x + sde_noise * sigmas[i + 1] * s_noise return x +@torch.no_grad() +def sample_exp_heun_2_x0(model, x, sigmas, extra_args=None, callback=None, disable=None, solver_type="phi_2"): + """Deterministic exponential Heun second order method in data prediction (x0) and logSNR time.""" + return sample_seeds_2(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=0.0, s_noise=0.0, noise_sampler=None, r=1.0, solver_type=solver_type) + + +@torch.no_grad() +def sample_exp_heun_2_x0_sde(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, solver_type="phi_2"): + """Stochastic exponential Heun second order method in data prediction (x0) and logSNR time.""" + return sample_seeds_2(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=eta, s_noise=s_noise, noise_sampler=noise_sampler, r=1.0, solver_type=solver_type) + @torch.no_grad() def sample_seeds_3(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, r_1=1./3, r_2=2./3): @@ -1765,7 +1776,7 @@ def sample_sa_solver(model, x, sigmas, extra_args=None, callback=None, disable=F # Predictor if sigmas[i + 1] == 0: # Denoising step - x = denoised + x_pred = denoised else: tau_t = tau_func(sigmas[i + 1]) curr_lambdas = lambdas[i - predictor_order_used + 1:i + 1] @@ -1786,7 +1797,7 @@ def sample_sa_solver(model, x, sigmas, extra_args=None, callback=None, disable=F if tau_t > 0 and s_noise > 0: noise = noise_sampler(sigmas[i], sigmas[i + 1]) * sigmas[i + 1] * (-2 * tau_t ** 2 * h).expm1().neg().sqrt() * s_noise x_pred = x_pred + noise - return x + return x_pred @torch.no_grad() diff --git a/comfy/samplers.py b/comfy/samplers.py index fa4640842..8340d376c 100755 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -720,7 +720,7 @@ class Sampler: sigma = float(sigmas[0]) return math.isclose(max_sigma, sigma, rel_tol=1e-05) or sigma > max_sigma -KSAMPLER_NAMES = ["euler", "euler_cfg_pp", "euler_ancestral", "euler_ancestral_cfg_pp", "heun", "heunpp2","dpm_2", "dpm_2_ancestral", +KSAMPLER_NAMES = ["euler", "euler_cfg_pp", "euler_ancestral", "euler_ancestral_cfg_pp", "heun", "heunpp2", "exp_heun_2_x0", "exp_heun_2_x0_sde", "dpm_2", "dpm_2_ancestral", "lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_2s_ancestral_cfg_pp", "dpmpp_sde", "dpmpp_sde_gpu", "dpmpp_2m", "dpmpp_2m_cfg_pp", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_2m_sde_heun", "dpmpp_2m_sde_heun_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm", "lcm", "ipndm", "ipndm_v", "deis", "res_multistep", "res_multistep_cfg_pp", "res_multistep_ancestral", "res_multistep_ancestral_cfg_pp", diff --git a/comfy_api/latest/_io.py b/comfy_api/latest/_io.py index 2b634d172..4b14e5ded 100644 --- a/comfy_api/latest/_io.py +++ b/comfy_api/latest/_io.py @@ -1556,12 +1556,12 @@ class _ComfyNodeBaseInternal(_ComfyNodeInternal): @final @classmethod - def PREPARE_CLASS_CLONE(cls, v3_data: V3Data) -> type[ComfyNode]: + def PREPARE_CLASS_CLONE(cls, v3_data: V3Data | None) -> type[ComfyNode]: """Creates clone of real node class to prevent monkey-patching.""" c_type: type[ComfyNode] = cls if is_class(cls) else type(cls) type_clone: type[ComfyNode] = shallow_clone_class(c_type) # set hidden - type_clone.hidden = HiddenHolder.from_dict(v3_data["hidden_inputs"]) + type_clone.hidden = HiddenHolder.from_dict(v3_data["hidden_inputs"] if v3_data else None) return type_clone @final diff --git a/comfy_api_nodes/apis/openai_api.py b/comfy_api_nodes/apis/openai_api.py new file mode 100644 index 000000000..ae5bb2673 --- /dev/null +++ b/comfy_api_nodes/apis/openai_api.py @@ -0,0 +1,52 @@ +from pydantic import BaseModel, Field + + +class Datum2(BaseModel): + b64_json: str | None = Field(None, description="Base64 encoded image data") + revised_prompt: str | None = Field(None, description="Revised prompt") + url: str | None = Field(None, description="URL of the image") + + +class InputTokensDetails(BaseModel): + image_tokens: int | None = None + text_tokens: int | None = None + + +class Usage(BaseModel): + input_tokens: int | None = None + input_tokens_details: InputTokensDetails | None = None + output_tokens: int | None = None + total_tokens: int | None = None + + +class OpenAIImageGenerationResponse(BaseModel): + data: list[Datum2] | None = None + usage: Usage | None = None + + +class OpenAIImageEditRequest(BaseModel): + background: str | None = Field(None, description="Background transparency") + model: str = Field(...) + moderation: str | None = Field(None) + n: int | None = Field(None, description="The number of images to generate") + output_compression: int | None = Field(None, description="Compression level for JPEG or WebP (0-100)") + output_format: str | None = Field(None) + prompt: str = Field(...) + quality: str | None = Field(None, description="Size of the image (e.g., 1024x1024, 1536x1024, auto)") + size: str | None = Field(None, description="Size of the output image") + + +class OpenAIImageGenerationRequest(BaseModel): + background: str | None = Field(None, description="Background transparency") + model: str | None = Field(None) + moderation: str | None = Field(None) + n: int | None = Field( + None, + description="The number of images to generate.", + ) + output_compression: int | None = Field(None, description="Compression level for JPEG or WebP (0-100)") + output_format: str | None = Field(None) + prompt: str = Field(...) + quality: str | None = Field(None, description="The quality of the generated image") + size: str | None = Field(None, description="Size of the image (e.g., 1024x1024, 1536x1024, auto)") + style: str | None = Field(None, description="Style of the image (only for dall-e-3)") diff --git a/comfy_api_nodes/nodes_openai.py b/comfy_api_nodes/nodes_openai.py index c8da5464b..a6205a34f 100644 --- a/comfy_api_nodes/nodes_openai.py +++ b/comfy_api_nodes/nodes_openai.py @@ -1,46 +1,45 @@ -from io import BytesIO +import base64 import os from enum import Enum -from inspect import cleandoc +from io import BytesIO + import numpy as np import torch from PIL import Image -import folder_paths -import base64 -from comfy_api.latest import IO, ComfyExtension from typing_extensions import override - +import folder_paths +from comfy_api.latest import IO, ComfyExtension, Input from comfy_api_nodes.apis import ( - OpenAIImageGenerationRequest, - OpenAIImageEditRequest, - OpenAIImageGenerationResponse, - OpenAICreateResponse, - OpenAIResponse, CreateModelResponseProperties, - Item, - OutputContent, - InputImageContent, Detail, - InputTextContent, - InputMessage, - InputMessageContentList, InputContent, InputFileContent, + InputImageContent, + InputMessage, + InputMessageContentList, + InputTextContent, + Item, + OpenAICreateResponse, + OpenAIResponse, + OutputContent, +) +from comfy_api_nodes.apis.openai_api import ( + OpenAIImageEditRequest, + OpenAIImageGenerationRequest, + OpenAIImageGenerationResponse, ) - from comfy_api_nodes.util import ( - downscale_image_tensor, - download_url_to_bytesio, - validate_string, - tensor_to_base64_string, ApiEndpoint, - sync_op, + download_url_to_bytesio, + downscale_image_tensor, poll_op, + sync_op, + tensor_to_base64_string, text_filepath_to_data_uri, + validate_string, ) - RESPONSES_ENDPOINT = "/proxy/openai/v1/responses" STARTING_POINT_ID_PATTERN = r"" @@ -98,9 +97,6 @@ async def validate_and_cast_response(response, timeout: int = None) -> torch.Ten class OpenAIDalle2(IO.ComfyNode): - """ - Generates images synchronously via OpenAI's DALL·E 2 endpoint. - """ @classmethod def define_schema(cls): @@ -108,7 +104,7 @@ class OpenAIDalle2(IO.ComfyNode): node_id="OpenAIDalle2", display_name="OpenAI DALL·E 2", category="api node/image/OpenAI", - description=cleandoc(cls.__doc__ or ""), + description="Generates images synchronously via OpenAI's DALL·E 2 endpoint.", inputs=[ IO.String.Input( "prompt", @@ -234,9 +230,6 @@ class OpenAIDalle2(IO.ComfyNode): class OpenAIDalle3(IO.ComfyNode): - """ - Generates images synchronously via OpenAI's DALL·E 3 endpoint. - """ @classmethod def define_schema(cls): @@ -244,7 +237,7 @@ class OpenAIDalle3(IO.ComfyNode): node_id="OpenAIDalle3", display_name="OpenAI DALL·E 3", category="api node/image/OpenAI", - description=cleandoc(cls.__doc__ or ""), + description="Generates images synchronously via OpenAI's DALL·E 3 endpoint.", inputs=[ IO.String.Input( "prompt", @@ -326,10 +319,16 @@ class OpenAIDalle3(IO.ComfyNode): return IO.NodeOutput(await validate_and_cast_response(response)) +def calculate_tokens_price_image_1(response: OpenAIImageGenerationResponse) -> float | None: + # https://platform.openai.com/docs/pricing + return ((response.usage.input_tokens * 10.0) + (response.usage.output_tokens * 40.0)) / 1_000_000.0 + + +def calculate_tokens_price_image_1_5(response: OpenAIImageGenerationResponse) -> float | None: + return ((response.usage.input_tokens * 8.0) + (response.usage.output_tokens * 32.0)) / 1_000_000.0 + + class OpenAIGPTImage1(IO.ComfyNode): - """ - Generates images synchronously via OpenAI's GPT Image 1 endpoint. - """ @classmethod def define_schema(cls): @@ -337,13 +336,13 @@ class OpenAIGPTImage1(IO.ComfyNode): node_id="OpenAIGPTImage1", display_name="OpenAI GPT Image 1", category="api node/image/OpenAI", - description=cleandoc(cls.__doc__ or ""), + description="Generates images synchronously via OpenAI's GPT Image 1 endpoint.", inputs=[ IO.String.Input( "prompt", default="", multiline=True, - tooltip="Text prompt for GPT Image 1", + tooltip="Text prompt for GPT Image", ), IO.Int.Input( "seed", @@ -365,8 +364,8 @@ class OpenAIGPTImage1(IO.ComfyNode): ), IO.Combo.Input( "background", - default="opaque", - options=["opaque", "transparent"], + default="auto", + options=["auto", "opaque", "transparent"], tooltip="Return image with or without background", optional=True, ), @@ -397,6 +396,11 @@ class OpenAIGPTImage1(IO.ComfyNode): tooltip="Optional mask for inpainting (white areas will be replaced)", optional=True, ), + IO.Combo.Input( + "model", + options=["gpt-image-1", "gpt-image-1.5"], + optional=True, + ), ], outputs=[ IO.Image.Output(), @@ -412,32 +416,34 @@ class OpenAIGPTImage1(IO.ComfyNode): @classmethod async def execute( cls, - prompt, - seed=0, - quality="low", - background="opaque", - image=None, - mask=None, - n=1, - size="1024x1024", + prompt: str, + seed: int = 0, + quality: str = "low", + background: str = "opaque", + image: Input.Image | None = None, + mask: Input.Image | None = None, + n: int = 1, + size: str = "1024x1024", + model: str = "gpt-image-1", ) -> IO.NodeOutput: validate_string(prompt, strip_whitespace=False) - model = "gpt-image-1" - path = "/proxy/openai/images/generations" - content_type = "application/json" - request_class = OpenAIImageGenerationRequest - files = [] + + if mask is not None and image is None: + raise ValueError("Cannot use a mask without an input image") + + if model == "gpt-image-1": + price_extractor = calculate_tokens_price_image_1 + elif model == "gpt-image-1.5": + price_extractor = calculate_tokens_price_image_1_5 + else: + raise ValueError(f"Unknown model: {model}") if image is not None: - path = "/proxy/openai/images/edits" - request_class = OpenAIImageEditRequest - content_type = "multipart/form-data" - + files = [] batch_size = image.shape[0] - for i in range(batch_size): - single_image = image[i : i + 1] - scaled_image = downscale_image_tensor(single_image).squeeze() + single_image = image[i: i + 1] + scaled_image = downscale_image_tensor(single_image, total_pixels=2048*2048).squeeze() image_np = (scaled_image.numpy() * 255).astype(np.uint8) img = Image.fromarray(image_np) @@ -450,44 +456,59 @@ class OpenAIGPTImage1(IO.ComfyNode): else: files.append(("image[]", (f"image_{i}.png", img_byte_arr, "image/png"))) - if mask is not None: - if image is None: - raise Exception("Cannot use a mask without an input image") - if image.shape[0] != 1: - raise Exception("Cannot use a mask with multiple image") - if mask.shape[1:] != image.shape[1:-1]: - raise Exception("Mask and Image must be the same size") - batch, height, width = mask.shape - rgba_mask = torch.zeros(height, width, 4, device="cpu") - rgba_mask[:, :, 3] = 1 - mask.squeeze().cpu() + if mask is not None: + if image.shape[0] != 1: + raise Exception("Cannot use a mask with multiple image") + if mask.shape[1:] != image.shape[1:-1]: + raise Exception("Mask and Image must be the same size") + _, height, width = mask.shape + rgba_mask = torch.zeros(height, width, 4, device="cpu") + rgba_mask[:, :, 3] = 1 - mask.squeeze().cpu() - scaled_mask = downscale_image_tensor(rgba_mask.unsqueeze(0)).squeeze() + scaled_mask = downscale_image_tensor(rgba_mask.unsqueeze(0), total_pixels=2048*2048).squeeze() - mask_np = (scaled_mask.numpy() * 255).astype(np.uint8) - mask_img = Image.fromarray(mask_np) - mask_img_byte_arr = BytesIO() - mask_img.save(mask_img_byte_arr, format="PNG") - mask_img_byte_arr.seek(0) - files.append(("mask", ("mask.png", mask_img_byte_arr, "image/png"))) - - # Build the operation - response = await sync_op( - cls, - ApiEndpoint(path=path, method="POST"), - response_model=OpenAIImageGenerationResponse, - data=request_class( - model=model, - prompt=prompt, - quality=quality, - background=background, - n=n, - seed=seed, - size=size, - ), - files=files if files else None, - content_type=content_type, - ) + mask_np = (scaled_mask.numpy() * 255).astype(np.uint8) + mask_img = Image.fromarray(mask_np) + mask_img_byte_arr = BytesIO() + mask_img.save(mask_img_byte_arr, format="PNG") + mask_img_byte_arr.seek(0) + files.append(("mask", ("mask.png", mask_img_byte_arr, "image/png"))) + response = await sync_op( + cls, + ApiEndpoint(path="/proxy/openai/images/edits", method="POST"), + response_model=OpenAIImageGenerationResponse, + data=OpenAIImageEditRequest( + model=model, + prompt=prompt, + quality=quality, + background=background, + n=n, + seed=seed, + size=size, + moderation="low", + ), + content_type="multipart/form-data", + files=files, + price_extractor=price_extractor, + ) + else: + response = await sync_op( + cls, + ApiEndpoint(path="/proxy/openai/images/generations", method="POST"), + response_model=OpenAIImageGenerationResponse, + data=OpenAIImageGenerationRequest( + model=model, + prompt=prompt, + quality=quality, + background=background, + n=n, + seed=seed, + size=size, + moderation="low", + ), + price_extractor=price_extractor, + ) return IO.NodeOutput(await validate_and_cast_response(response)) diff --git a/comfy_api_nodes/util/conversions.py b/comfy_api_nodes/util/conversions.py index c57457580..d64239c86 100644 --- a/comfy_api_nodes/util/conversions.py +++ b/comfy_api_nodes/util/conversions.py @@ -129,7 +129,7 @@ def pil_to_bytesio(img: Image.Image, mime_type: str = "image/png") -> BytesIO: return img_byte_arr -def downscale_image_tensor(image, total_pixels=1536 * 1024) -> torch.Tensor: +def downscale_image_tensor(image: torch.Tensor, total_pixels: int = 1536 * 1024) -> torch.Tensor: """Downscale input image tensor to roughly the specified total pixels.""" samples = image.movedim(-1, 1) total = int(total_pixels) diff --git a/comfy_extras/nodes_custom_sampler.py b/comfy_extras/nodes_custom_sampler.py index 71ea4e9ec..7ee4caac1 100644 --- a/comfy_extras/nodes_custom_sampler.py +++ b/comfy_extras/nodes_custom_sampler.py @@ -671,7 +671,16 @@ class SamplerSEEDS2(io.ComfyNode): io.Float.Input("s_noise", default=1.0, min=0.0, max=100.0, step=0.01, round=False, tooltip="SDE noise multiplier"), io.Float.Input("r", default=0.5, min=0.01, max=1.0, step=0.01, round=False, tooltip="Relative step size for the intermediate stage (c2 node)"), ], - outputs=[io.Sampler.Output()] + outputs=[io.Sampler.Output()], + description=( + "This sampler node can represent multiple samplers:\n\n" + "seeds_2\n" + "- default setting\n\n" + "exp_heun_2_x0\n" + "- solver_type=phi_2, r=1.0, eta=0.0\n\n" + "exp_heun_2_x0_sde\n" + "- solver_type=phi_2, r=1.0, eta=1.0, s_noise=1.0" + ) ) @classmethod diff --git a/comfyui_version.py b/comfyui_version.py index 2f083edaf..5edf270e7 100644 --- a/comfyui_version.py +++ b/comfyui_version.py @@ -1,3 +1,3 @@ # This file is automatically generated by the build process when version is # updated in pyproject.toml. -__version__ = "0.4.0" +__version__ = "0.5.0" diff --git a/pyproject.toml b/pyproject.toml index e4d3d616a..c402f278c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "ComfyUI" -version = "0.4.0" +version = "0.5.0" readme = "README.md" license = { file = "LICENSE" } requires-python = ">=3.9"