diff --git a/comfy_api_nodes/apis/bytedance.py b/comfy_api_nodes/apis/bytedance.py index 2d65d8645..5267395a1 100644 --- a/comfy_api_nodes/apis/bytedance.py +++ b/comfy_api_nodes/apis/bytedance.py @@ -1,4 +1,4 @@ -from typing import Literal +from typing import Any, Literal from pydantic import BaseModel, Field @@ -316,3 +316,36 @@ VIDEO_TASKS_EXECUTION_TIME = { "1080p": 150, }, } + + +class SeedAudioConfig(BaseModel): + format: str = Field(default="mp3") + sample_rate: int = Field(default=24000) + speech_rate: int = Field(default=0) + loudness_rate: int = Field(default=0) + pitch_rate: int = Field(default=0) + + +class SeedAudioReference(BaseModel): + speaker: str | None = Field(default=None) + audio_data: str | None = Field(default=None) + audio_url: str | None = Field(default=None) + image_data: str | None = Field(default=None) + image_url: str | None = Field(default=None) + + +class SeedAudioRequest(BaseModel): + model: str = Field(default="seed-audio-1.0") + text_prompt: str = Field(...) + references: list[SeedAudioReference] | None = Field(default=None) + audio_config: SeedAudioConfig = Field(default_factory=SeedAudioConfig) + watermark: dict[str, Any] = Field(default_factory=dict) + + +class SeedAudioResponse(BaseModel): + audio: str | None = Field(default=None) + url: str | None = Field(default=None) + duration: float | None = Field(default=None) + original_duration: float | None = Field(default=None) + code: int | None = Field(default=None) + message: str | None = Field(default=None) diff --git a/comfy_api_nodes/apis/stability.py b/comfy_api_nodes/apis/stability.py deleted file mode 100644 index 5b9b5ac7d..000000000 --- a/comfy_api_nodes/apis/stability.py +++ /dev/null @@ -1,147 +0,0 @@ -from enum import Enum -from typing import Optional - -from pydantic import BaseModel, Field, confloat - - -class StabilityFormat(str, Enum): - png = 'png' - jpeg = 'jpeg' - webp = 'webp' - - -class StabilityAspectRatio(str, Enum): - ratio_1_1 = "1:1" - ratio_16_9 = "16:9" - ratio_9_16 = "9:16" - ratio_3_2 = "3:2" - ratio_2_3 = "2:3" - ratio_5_4 = "5:4" - ratio_4_5 = "4:5" - ratio_21_9 = "21:9" - ratio_9_21 = "9:21" - - -def get_stability_style_presets(include_none=True): - presets = [] - if include_none: - presets.append("None") - return presets + [x.value for x in StabilityStylePreset] - - -class StabilityStylePreset(str, Enum): - _3d_model = "3d-model" - analog_film = "analog-film" - anime = "anime" - cinematic = "cinematic" - comic_book = "comic-book" - digital_art = "digital-art" - enhance = "enhance" - fantasy_art = "fantasy-art" - isometric = "isometric" - line_art = "line-art" - low_poly = "low-poly" - modeling_compound = "modeling-compound" - neon_punk = "neon-punk" - origami = "origami" - photographic = "photographic" - pixel_art = "pixel-art" - tile_texture = "tile-texture" - - -class Stability_SD3_5_Model(str, Enum): - sd3_5_large = "sd3.5-large" - # sd3_5_large_turbo = "sd3.5-large-turbo" - sd3_5_medium = "sd3.5-medium" - - -class Stability_SD3_5_GenerationMode(str, Enum): - text_to_image = "text-to-image" - image_to_image = "image-to-image" - - -class StabilityStable3_5Request(BaseModel): - model: str = Field(...) - mode: str = Field(...) - prompt: str = Field(...) - negative_prompt: Optional[str] = Field(None) - aspect_ratio: Optional[str] = Field(None) - seed: Optional[int] = Field(None) - output_format: Optional[str] = Field(StabilityFormat.png.value) - image: Optional[str] = Field(None) - style_preset: Optional[str] = Field(None) - cfg_scale: float = Field(...) - strength: Optional[confloat(ge=0.0, le=1.0)] = Field(None) - - -class StabilityUpscaleConservativeRequest(BaseModel): - prompt: str = Field(...) - negative_prompt: Optional[str] = Field(None) - seed: Optional[int] = Field(None) - output_format: Optional[str] = Field(StabilityFormat.png.value) - image: Optional[str] = Field(None) - creativity: Optional[confloat(ge=0.2, le=0.5)] = Field(None) - - -class StabilityUpscaleCreativeRequest(BaseModel): - prompt: str = Field(...) - negative_prompt: Optional[str] = Field(None) - seed: Optional[int] = Field(None) - output_format: Optional[str] = Field(StabilityFormat.png.value) - image: Optional[str] = Field(None) - creativity: Optional[confloat(ge=0.1, le=0.5)] = Field(None) - style_preset: Optional[str] = Field(None) - - -class StabilityStableUltraRequest(BaseModel): - prompt: str = Field(...) - negative_prompt: Optional[str] = Field(None) - aspect_ratio: Optional[str] = Field(None) - seed: Optional[int] = Field(None) - output_format: Optional[str] = Field(StabilityFormat.png.value) - image: Optional[str] = Field(None) - style_preset: Optional[str] = Field(None) - strength: Optional[confloat(ge=0.0, le=1.0)] = Field(None) - - -class StabilityStableUltraResponse(BaseModel): - image: Optional[str] = Field(None) - finish_reason: Optional[str] = Field(None) - seed: Optional[int] = Field(None) - - -class StabilityResultsGetResponse(BaseModel): - image: Optional[str] = Field(None) - finish_reason: Optional[str] = Field(None) - seed: Optional[int] = Field(None) - id: Optional[str] = Field(None) - name: Optional[str] = Field(None) - errors: Optional[list[str]] = Field(None) - status: Optional[str] = Field(None) - result: Optional[str] = Field(None) - - -class StabilityAsyncResponse(BaseModel): - id: Optional[str] = Field(None) - - -class StabilityTextToAudioRequest(BaseModel): - model: str = Field(...) - prompt: str = Field(...) - duration: int = Field(190, ge=1, le=190) - seed: int = Field(0, ge=0, le=4294967294) - steps: int = Field(8, ge=4, le=8) - output_format: str = Field("wav") - - -class StabilityAudioToAudioRequest(StabilityTextToAudioRequest): - strength: float = Field(0.01, ge=0.01, le=1.0) - - -class StabilityAudioInpaintRequest(StabilityTextToAudioRequest): - mask_start: int = Field(30, ge=0, le=190) - mask_end: int = Field(190, ge=0, le=190) - - -class StabilityAudioResponse(BaseModel): - audio: Optional[str] = Field(None) diff --git a/comfy_api_nodes/nodes_bytedance.py b/comfy_api_nodes/nodes_bytedance.py index f22415abd..a67883555 100644 --- a/comfy_api_nodes/nodes_bytedance.py +++ b/comfy_api_nodes/nodes_bytedance.py @@ -1,3 +1,4 @@ +import base64 import hashlib import logging import math @@ -20,6 +21,10 @@ from comfy_api_nodes.apis.bytedance import ( GetAssetResponse, Image2VideoTaskCreationRequest, ImageTaskCreationResponse, + SeedAudioConfig, + SeedAudioReference, + SeedAudioRequest, + SeedAudioResponse, Seedance2TaskCreationRequest, SeedanceCreateAssetRequest, SeedanceCreateAssetResponse, @@ -43,6 +48,8 @@ from comfy_api_nodes.apis.bytedance import ( ) from comfy_api_nodes.util import ( ApiEndpoint, + audio_bytes_to_audio_input, + audio_input_to_mp3, download_url_to_image_tensor, download_url_to_video_output, downscale_image_tensor_by_max_side, @@ -51,11 +58,14 @@ from comfy_api_nodes.util import ( image_tensor_pair_to_batch, poll_op, sync_op, + tensor_to_base64_string, upload_audio_to_comfyapi, upload_image_to_comfyapi, upload_images_to_comfyapi, upload_video_to_comfyapi, + upscale_image_tensor_to_min_pixels, upscale_video_to_min_pixels, + validate_audio_duration, validate_image_aspect_ratio, validate_image_dimensions, validate_string, @@ -2474,6 +2484,311 @@ class ByteDanceCreateVideoAsset(IO.ComfyNode): return IO.NodeOutput(asset_id, resolved_group) +MODE_TEXT = "text only" +MODE_AUDIO = "audio reference" +MODE_IMAGE = "image reference" +MODE_SPEAKER = "preset voice" + +# (speaker_id, display_label) for built-in TTS 2.0 voices; resolvable ids are account-scoped. +SEED_AUDIO_PRESET_VOICES: list[tuple[str, str]] = [ + ("zh_female_vv_uranus_bigtts", "Vivi (Female, multilingual)"), + ("zh_female_xiaohe_uranus_bigtts", "Mindy (Female, multilingual)"), + ("en_female_stokie_uranus_bigtts", "Stokie (Female, English)"), + ("en_female_dacey_uranus_bigtts", "Dacey (Female, English)"), + ("en_male_tim_uranus_bigtts", "Tim (Male, English)"), + ("zh_male_m191_uranus_bigtts", "Kian (Male, multilingual)"), + ("zh_male_taocheng_uranus_bigtts", "Cedric (Male, multilingual)"), + ("zh_male_sophie_uranus_bigtts", "Sophie (Female, multilingual)"), + ("zh_female_yingyujiaoxue_uranus_bigtts", "Jean (Female, multilingual)"), + ("zh_male_dayi_uranus_bigtts", "Magnus (Male, multilingual)"), + ("zh_female_mizai_uranus_bigtts", "Mabel (Female, multilingual)"), + ("zh_female_jitangnv_uranus_bigtts", "Nadia (Female, multilingual)"), + ("zh_female_meilinvyou_uranus_bigtts", "Opal (Female, multilingual)"), + ("zh_female_liuchangnv_uranus_bigtts", "Pearl (Female, multilingual)"), + ("zh_male_ruyayichen_uranus_bigtts", "Quentin (Male, multilingual)"), + ("zh_female_vivo_uranus_bigtts", "Vienna (Female, multilingual)"), + ("zh_female_xiaoai_uranus_bigtts", "Alina (Female, multilingual)"), + ("zh_female_cancan_uranus_bigtts", "Corinne (Female, multilingual)"), + ("zh_female_tianmeixiaoyuan_uranus_bigtts", "Esther (Female, multilingual)"), + ("zh_female_tianmeitaozi_uranus_bigtts", "Freya (Female, multilingual)"), + ("zh_female_shuangkuaisisi_uranus_bigtts", "Gigi (Female, multilingual)"), + ("zh_female_peiqi_uranus_bigtts", "Holly (Female, multilingual)"), + ("zh_female_xiaoxue_uranus_bigtts", "Lyla (Female, multilingual)"), + ("zh_female_yuanqi_uranus_bigtts", "Daisy (Female, multilingual)"), + ("zh_female_kefunvsheng_uranus_bigtts", "Tracy (Female, multilingual)"), + ("zh_male_shaonianzixin_uranus_bigtts", "Jess (Male, multilingual)"), + ("zh_female_linjianvhai_uranus_bigtts", "Pinky (Female, multilingual)"), + ("zh_female_kiwi_uranus_bigtts", "Sweety (Female, multilingual)"), + ("zh_female_sajiaoxuemei_uranus_bigtts", "Sandy (Female, multilingual)"), + ("de_male_seven_uranus_bigtts", "Sven (Male, German)"), + ("jp_female_minimi_uranus_bigtts", "Minimi (Female, Japanese)"), + ("fr_male_usseau_uranus_bigtts", "Usseau (Male, French)"), + ("es_male_felipe_uranus_bigtts", "Felipe (Male, Spanish)"), + ("id_male_han_uranus_bigtts", "Han (Male, Indonesian)"), + ("pt_male_martins_uranus_bigtts", "Martins (Male, Portuguese)"), + ("it_male_enzo_uranus_bigtts", "Enzo (Male, Italian)"), + ("kr_male_shane_uranus_bigtts", "Shane (Male, Korean)"), + ("zh_male_liufei_uranus_bigtts", "Felix (Male, Chinese)"), + ("zh_female_qingxinnvsheng_uranus_bigtts", "Celeste (Female, Chinese)"), + ("zh_male_sunwukong_uranus_bigtts", "Monkey King (Male, Chinese)"), +] +SEED_AUDIO_VOICE_OPTIONS = [label for _, label in SEED_AUDIO_PRESET_VOICES] +SEED_AUDIO_VOICE_MAP = {label: speaker_id for speaker_id, label in SEED_AUDIO_PRESET_VOICES} + +_AUDIO_TAG_RE = re.compile(r"@Audio(\d+)", re.IGNORECASE) + + +def max_audio_tag(prompt: str) -> int: + """Highest N referenced as @AudioN in the prompt (0 if none).""" + nums = [int(m) for m in _AUDIO_TAG_RE.findall(prompt or "")] + return max(nums) if nums else 0 + + +def connected_audio_indices(reference_mode: dict) -> list[int]: + """Indices (1-based) of connected reference_audio sockets, in order.""" + return [ + i + for i in range(1, 3 + 1) + if reference_mode.get(f"reference_audio_{i}") is not None + ] + + +def validate_seed_audio_inputs( + text_prompt: str, + mode: str, + audio_indices: list[int], + has_image: bool, + preset_voice: str | None = None, +) -> None: + validate_string(text_prompt, field_name="text_prompt", min_length=1, max_length=3000) + max_tag = max_audio_tag(text_prompt) + + if mode == MODE_TEXT: + if max_tag: + raise ValueError( + f"The prompt references @Audio{max_tag}, but reference mode is '{MODE_TEXT}'. " + f"Switch to '{MODE_AUDIO}' and connect the reference clip(s)." + ) + elif mode == MODE_AUDIO: + if not audio_indices: + raise ValueError( + f"Reference mode '{MODE_AUDIO}' requires at least one reference_audio input " + f"(or switch to '{MODE_TEXT}')." + ) + if audio_indices != list(range(1, len(audio_indices) + 1)): + raise ValueError( + "Connect reference_audio inputs in order without gaps: reference_audio_1, then _2, then _3." + ) + if max_tag > len(audio_indices): + raise ValueError( + f"The prompt references @Audio{max_tag}, but only {len(audio_indices)} " + f"reference audio(s) are connected." + ) + elif mode == MODE_IMAGE: + if not has_image: + raise ValueError(f"Reference mode '{MODE_IMAGE}' requires a reference_image input.") + if max_tag: + raise ValueError( + f"@AudioN tags are not used in '{MODE_IMAGE}' mode; the prompt should contain " + f"only the text to synthesize." + ) + elif mode == MODE_SPEAKER: + if not preset_voice or preset_voice not in SEED_AUDIO_VOICE_MAP: + raise ValueError(f"Reference mode '{MODE_SPEAKER}' requires selecting a preset voice.") + if max_tag > 1: + raise ValueError( + f"'{MODE_SPEAKER}' mode uses a single voice, so @Audio{max_tag} is out of range. " + f"Remove the @AudioN tags — the whole prompt is read in the selected voice." + ) + else: + raise ValueError(f"Unknown reference mode: {mode!r}") + + +class ByteDanceSeedAudioNode(IO.ComfyNode): + + @classmethod + def define_schema(cls) -> IO.Schema: + return IO.Schema( + node_id="ByteDanceSeedAudio", + display_name="ByteDance Seed Audio 1.0", + category="api node/audio/ByteDance", + description=( + "Generate speech, music, sound effects and multi-speaker dialogue from a single prompt " + "with ByteDance Seed Audio 1.0. Describe the voice(s), emotion, ambience, background music " + "and sound effects in the prompt, and include the lines to speak. Optionally pick a built-in " + "preset voice, clone voices from up to 3 reference clips (tagged @Audio1-3 in the prompt), " + "or derive a voice from a character image. Up to 2 minutes of audio per run." + ), + inputs=[ + IO.String.Input( + "text_prompt", + multiline=True, + default="", + tooltip=( + "Describe the voice(s), emotion, pacing, ambience, background music and sound " + "effects, and include the lines to speak (name characters inline for dialogue). " + "In 'audio reference' mode, refer to connected clips by order as @Audio1, @Audio2, " + "@Audio3. Maximum 3000 characters." + ), + ), + IO.DynamicCombo.Input( + "reference_mode", + options=[ + IO.DynamicCombo.Option(MODE_TEXT, []), + IO.DynamicCombo.Option( + MODE_AUDIO, + [ + IO.Audio.Input( + "reference_audio_1", + optional=True, + tooltip="Reference clip for voice cloning, tagged @Audio1 in the prompt. " + "Up to 30s.", + ), + IO.Audio.Input( + "reference_audio_2", + optional=True, + tooltip="Reference clip tagged @Audio2 in the prompt. Up to 30s.", + ), + IO.Audio.Input( + "reference_audio_3", + optional=True, + tooltip="Reference clip tagged @Audio3 in the prompt. Up to 30s.", + ), + ], + ), + IO.DynamicCombo.Option( + MODE_IMAGE, + [ + IO.Image.Input( + "reference_image", + optional=True, + tooltip="A single character image; the model derives a voice from it. " + "Cannot be combined with reference audio.", + ), + ], + ), + IO.DynamicCombo.Option( + MODE_SPEAKER, + [ + IO.Combo.Input( + "preset_voice", + options=SEED_AUDIO_VOICE_OPTIONS, + default=SEED_AUDIO_VOICE_OPTIONS[0], + tooltip="A built-in TTS 2.0 voice that reads the prompt. No reference " + "clip needed, and @AudioN tags are not used in this mode.", + ), + ], + ), + ], + tooltip=( + "How to condition the voice: 'text only' (describe everything in the prompt), " + "'audio reference' (clone up to 3 voices, tagged @Audio1-3), 'image reference' " + "(derive a voice from one character image), or 'preset voice' (pick a built-in " + "named voice that reads the prompt)." + ), + ), + IO.Combo.Input( + "sample_rate", + options=["8000", "16000", "24000", "32000", "44100", "48000"], + default="24000", + tooltip="Output sample rate in Hz.", + ), + IO.Int.Input( + "speech_rate", + default=0, + min=-50, + max=100, + tooltip="Speaking speed. 0 = normal, 100 = 2.0x, -50 = 0.5x.", + ), + IO.Int.Input( + "loudness_rate", + default=0, + min=-50, + max=100, + tooltip="Loudness. 0 = normal, 100 = 2.0x, -50 = 0.5x.", + ), + IO.Int.Input( + "pitch_rate", + default=0, + min=-12, + max=12, + tooltip="Pitch shift in semitones (-12 to 12).", + ), + IO.Int.Input( + "seed", + default=42, + min=0, + max=2147483647, + control_after_generate=True, + tooltip="Seed controls whether the node should re-run; " + "results are non-deterministic regardless of seed.", + ), + ], + outputs=[IO.Audio.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( + expr="""{"type":"usd","usd": 0.2145, "format":{"suffix":"/minute","approximate":true}}""", + ), + ) + + @classmethod + async def execute( + cls, + text_prompt: str, + reference_mode: dict, + sample_rate: str, + speech_rate: int, + loudness_rate: int, + pitch_rate: int, + seed: int, + ) -> IO.NodeOutput: + mode = reference_mode["reference_mode"] + audio_indices = connected_audio_indices(reference_mode) + image = reference_mode.get("reference_image") + preset_voice = reference_mode.get("preset_voice") + validate_seed_audio_inputs(text_prompt, mode, audio_indices, image is not None, preset_voice) + + references: list[SeedAudioReference] | None = None + if mode == MODE_AUDIO: + references = [] + for i in audio_indices: + clip = reference_mode[f"reference_audio_{i}"] + validate_audio_duration(clip, max_duration=30.0) + mp3_bytes = audio_input_to_mp3(clip).getvalue() + references.append(SeedAudioReference(audio_data=base64.b64encode(mp3_bytes).decode("utf-8"))) + elif mode == MODE_IMAGE: + image = upscale_image_tensor_to_min_pixels(image, 160_000) + references = [SeedAudioReference(image_data=tensor_to_base64_string(image, mime_type="image/png"))] + elif mode == MODE_SPEAKER: + references = [SeedAudioReference(speaker=SEED_AUDIO_VOICE_MAP[preset_voice])] + + response = await sync_op( + cls, + ApiEndpoint(path="/proxy/byteplus/api/v3/tts/create", method="POST"), + response_model=SeedAudioResponse, + data=SeedAudioRequest( + text_prompt=text_prompt, + references=references, + audio_config=SeedAudioConfig( + sample_rate=int(sample_rate), + speech_rate=speech_rate, + loudness_rate=loudness_rate, + pitch_rate=pitch_rate, + ), + ), + ) + if not response.audio: + raise Exception( + f"Seed Audio returned no audio (code={response.code}): {response.message}" + ) + return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response.audio))) + + class ByteDanceExtension(ComfyExtension): @override async def get_node_list(self) -> list[type[IO.ComfyNode]]: @@ -2490,6 +2805,7 @@ class ByteDanceExtension(ComfyExtension): ByteDance2ReferenceNode, ByteDanceCreateImageAsset, ByteDanceCreateVideoAsset, + ByteDanceSeedAudioNode, ] diff --git a/comfy_api_nodes/nodes_stability.py b/comfy_api_nodes/nodes_stability.py deleted file mode 100644 index 9eaba173b..000000000 --- a/comfy_api_nodes/nodes_stability.py +++ /dev/null @@ -1,932 +0,0 @@ -from inspect import cleandoc -from typing import Optional -from typing_extensions import override - -from comfy_api.latest import ComfyExtension, Input, IO -from comfy_api_nodes.apis.stability import ( - StabilityUpscaleConservativeRequest, - StabilityUpscaleCreativeRequest, - StabilityAsyncResponse, - StabilityResultsGetResponse, - StabilityStable3_5Request, - StabilityStableUltraRequest, - StabilityStableUltraResponse, - StabilityAspectRatio, - Stability_SD3_5_Model, - Stability_SD3_5_GenerationMode, - get_stability_style_presets, - StabilityTextToAudioRequest, - StabilityAudioToAudioRequest, - StabilityAudioInpaintRequest, - StabilityAudioResponse, -) -from comfy_api_nodes.util import ( - validate_audio_duration, - validate_string, - audio_input_to_mp3, - bytesio_to_image_tensor, - tensor_to_bytesio, - audio_bytes_to_audio_input, - sync_op, - poll_op, - ApiEndpoint, -) - -import torch -import base64 -from io import BytesIO -from enum import Enum - - -class StabilityPollStatus(str, Enum): - finished = "finished" - in_progress = "in_progress" - failed = "failed" - - -def get_async_dummy_status(x: StabilityResultsGetResponse): - if x.name is not None or x.errors is not None: - return StabilityPollStatus.failed - elif x.finish_reason is not None: - return StabilityPollStatus.finished - return StabilityPollStatus.in_progress - - -class StabilityStableImageUltraNode(IO.ComfyNode): - """ - Generates images synchronously based on prompt and resolution. - """ - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityStableImageUltraNode", - display_name="Stability AI Stable Image Ultra", - category="partner/image/Stability AI", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.String.Input( - "prompt", - multiline=True, - default="", - tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines" + - "elements, colors, and subjects will lead to better results. " + - "To control the weight of a given word use the format `(word:weight)`," + - "where `word` is the word you'd like to control the weight of and `weight`" + - "is a value between 0 and 1. For example: `The sky was a crisp (blue:0.3) and (green:0.8)`" + - "would convey a sky that was blue and green, but more green than blue.", - ), - IO.Combo.Input( - "aspect_ratio", - options=StabilityAspectRatio, - default=StabilityAspectRatio.ratio_1_1, - tooltip="Aspect ratio of generated image.", - ), - IO.Combo.Input( - "style_preset", - options=get_stability_style_presets(), - tooltip="Optional desired style of generated image.", - advanced=True, - ), - IO.Int.Input( - "seed", - default=0, - min=0, - max=4294967294, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="The random seed used for creating the noise.", - ), - IO.Image.Input( - "image", - optional=True, - ), - IO.String.Input( - "negative_prompt", - default="", - tooltip="A blurb of text describing what you do not wish to see in the output image. This is an advanced feature.", - force_input=True, - optional=True, - advanced=True, - ), - IO.Float.Input( - "image_denoise", - default=0.5, - min=0.0, - max=1.0, - step=0.01, - tooltip="Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.", - 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( - expr="""{"type":"usd","usd":0.08}""", - ), - ) - - @classmethod - async def execute( - cls, - prompt: str, - aspect_ratio: str, - style_preset: str, - seed: int, - image: Optional[torch.Tensor] = None, - negative_prompt: str = "", - image_denoise: Optional[float] = 0.5, - ) -> IO.NodeOutput: - validate_string(prompt, strip_whitespace=False) - # prepare image binary if image present - image_binary = None - if image is not None: - image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read() - else: - image_denoise = None - - if not negative_prompt: - negative_prompt = None - if style_preset == "None": - style_preset = None - - files = { - "image": image_binary - } - - response_api = await sync_op( - cls, - ApiEndpoint(path="/proxy/stability/v2beta/stable-image/generate/ultra", method="POST"), - response_model=StabilityStableUltraResponse, - data=StabilityStableUltraRequest( - prompt=prompt, - negative_prompt=negative_prompt, - aspect_ratio=aspect_ratio, - seed=seed, - strength=image_denoise, - style_preset=style_preset, - ), - files=files, - content_type="multipart/form-data", - ) - - if response_api.finish_reason != "SUCCESS": - raise Exception(f"Stable Image Ultra generation failed: {response_api.finish_reason}.") - - image_data = base64.b64decode(response_api.image) - returned_image = bytesio_to_image_tensor(BytesIO(image_data)) - - return IO.NodeOutput(returned_image) - - -class StabilityStableImageSD_3_5Node(IO.ComfyNode): - """ - Generates images synchronously based on prompt and resolution. - """ - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityStableImageSD_3_5Node", - display_name="Stability AI Stable Diffusion 3.5 Image", - category="partner/image/Stability AI", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.String.Input( - "prompt", - multiline=True, - default="", - tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.", - ), - IO.Combo.Input( - "model", - options=Stability_SD3_5_Model, - ), - IO.Combo.Input( - "aspect_ratio", - options=StabilityAspectRatio, - default=StabilityAspectRatio.ratio_1_1, - tooltip="Aspect ratio of generated image.", - ), - IO.Combo.Input( - "style_preset", - options=get_stability_style_presets(), - tooltip="Optional desired style of generated image.", - advanced=True, - ), - IO.Float.Input( - "cfg_scale", - default=4.0, - min=1.0, - max=10.0, - step=0.1, - tooltip="How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt)", - ), - IO.Int.Input( - "seed", - default=0, - min=0, - max=4294967294, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="The random seed used for creating the noise.", - ), - IO.Image.Input( - "image", - optional=True, - ), - IO.String.Input( - "negative_prompt", - default="", - tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.", - force_input=True, - optional=True, - advanced=True, - ), - IO.Float.Input( - "image_denoise", - default=0.5, - min=0.0, - max=1.0, - step=0.01, - tooltip="Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.", - 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=["model"]), - expr=""" - ( - $contains(widgets.model,"large") - ? {"type":"usd","usd":0.065} - : {"type":"usd","usd":0.035} - ) - """, - ), - ) - - @classmethod - async def execute( - cls, - model: str, - prompt: str, - aspect_ratio: str, - style_preset: str, - seed: int, - cfg_scale: float, - image: Optional[torch.Tensor] = None, - negative_prompt: str = "", - image_denoise: Optional[float] = 0.5, - ) -> IO.NodeOutput: - validate_string(prompt, strip_whitespace=False) - # prepare image binary if image present - image_binary = None - mode = Stability_SD3_5_GenerationMode.text_to_image - if image is not None: - image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read() - mode = Stability_SD3_5_GenerationMode.image_to_image - aspect_ratio = None - else: - image_denoise = None - - if not negative_prompt: - negative_prompt = None - if style_preset == "None": - style_preset = None - - files = { - "image": image_binary - } - - response_api = await sync_op( - cls, - ApiEndpoint(path="/proxy/stability/v2beta/stable-image/generate/sd3", method="POST"), - response_model=StabilityStableUltraResponse, - data=StabilityStable3_5Request( - prompt=prompt, - negative_prompt=negative_prompt, - aspect_ratio=aspect_ratio, - seed=seed, - strength=image_denoise, - style_preset=style_preset, - cfg_scale=cfg_scale, - model=model, - mode=mode, - ), - files=files, - content_type="multipart/form-data", - ) - - if response_api.finish_reason != "SUCCESS": - raise Exception(f"Stable Diffusion 3.5 Image generation failed: {response_api.finish_reason}.") - - image_data = base64.b64decode(response_api.image) - returned_image = bytesio_to_image_tensor(BytesIO(image_data)) - - return IO.NodeOutput(returned_image) - - -class StabilityUpscaleConservativeNode(IO.ComfyNode): - """ - Upscale image with minimal alterations to 4K resolution. - """ - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityUpscaleConservativeNode", - display_name="Stability AI Upscale Conservative", - category="partner/image/Stability AI", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.Image.Input("image"), - IO.String.Input( - "prompt", - multiline=True, - default="", - tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.", - ), - IO.Float.Input( - "creativity", - default=0.35, - min=0.2, - max=0.5, - step=0.01, - tooltip="Controls the likelihood of creating additional details not heavily conditioned by the init image.", - ), - IO.Int.Input( - "seed", - default=0, - min=0, - max=4294967294, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="The random seed used for creating the noise.", - ), - IO.String.Input( - "negative_prompt", - default="", - tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.", - force_input=True, - optional=True, - advanced=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( - expr="""{"type":"usd","usd":0.4}""", - ), - ) - - @classmethod - async def execute( - cls, - image: torch.Tensor, - prompt: str, - creativity: float, - seed: int, - negative_prompt: str = "", - ) -> IO.NodeOutput: - validate_string(prompt, strip_whitespace=False) - image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read() - - if not negative_prompt: - negative_prompt = None - - files = { - "image": image_binary - } - - response_api = await sync_op( - cls, - ApiEndpoint(path="/proxy/stability/v2beta/stable-image/upscale/conservative", method="POST"), - response_model=StabilityStableUltraResponse, - data=StabilityUpscaleConservativeRequest( - prompt=prompt, - negative_prompt=negative_prompt, - creativity=round(creativity,2), - seed=seed, - ), - files=files, - content_type="multipart/form-data", - ) - - if response_api.finish_reason != "SUCCESS": - raise Exception(f"Stability Upscale Conservative generation failed: {response_api.finish_reason}.") - - image_data = base64.b64decode(response_api.image) - returned_image = bytesio_to_image_tensor(BytesIO(image_data)) - - return IO.NodeOutput(returned_image) - - -class StabilityUpscaleCreativeNode(IO.ComfyNode): - """ - Upscale image with minimal alterations to 4K resolution. - """ - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityUpscaleCreativeNode", - display_name="Stability AI Upscale Creative", - category="partner/image/Stability AI", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.Image.Input("image"), - IO.String.Input( - "prompt", - multiline=True, - default="", - tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.", - ), - IO.Float.Input( - "creativity", - default=0.3, - min=0.1, - max=0.5, - step=0.01, - tooltip="Controls the likelihood of creating additional details not heavily conditioned by the init image.", - ), - IO.Combo.Input( - "style_preset", - options=get_stability_style_presets(), - tooltip="Optional desired style of generated image.", - advanced=True, - ), - IO.Int.Input( - "seed", - default=0, - min=0, - max=4294967294, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="The random seed used for creating the noise.", - ), - IO.String.Input( - "negative_prompt", - default="", - tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.", - force_input=True, - optional=True, - advanced=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( - expr="""{"type":"usd","usd":0.6}""", - ), - ) - - @classmethod - async def execute( - cls, - image: torch.Tensor, - prompt: str, - creativity: float, - style_preset: str, - seed: int, - negative_prompt: str = "", - ) -> IO.NodeOutput: - validate_string(prompt, strip_whitespace=False) - image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read() - - if not negative_prompt: - negative_prompt = None - if style_preset == "None": - style_preset = None - - files = { - "image": image_binary - } - - response_api = await sync_op( - cls, - ApiEndpoint(path="/proxy/stability/v2beta/stable-image/upscale/creative", method="POST"), - response_model=StabilityAsyncResponse, - data=StabilityUpscaleCreativeRequest( - prompt=prompt, - negative_prompt=negative_prompt, - creativity=round(creativity,2), - style_preset=style_preset, - seed=seed, - ), - files=files, - content_type="multipart/form-data", - ) - - response_poll = await poll_op( - cls, - ApiEndpoint(path=f"/proxy/stability/v2beta/results/{response_api.id}"), - response_model=StabilityResultsGetResponse, - poll_interval=3, - status_extractor=lambda x: get_async_dummy_status(x), - ) - - if response_poll.finish_reason != "SUCCESS": - raise Exception(f"Stability Upscale Creative generation failed: {response_poll.finish_reason}.") - - image_data = base64.b64decode(response_poll.result) - returned_image = bytesio_to_image_tensor(BytesIO(image_data)) - - return IO.NodeOutput(returned_image) - - -class StabilityUpscaleFastNode(IO.ComfyNode): - """ - Quickly upscales an image via Stability API call to 4x its original size; intended for upscaling low-quality/compressed images. - """ - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityUpscaleFastNode", - display_name="Stability AI Upscale Fast", - category="partner/image/Stability AI", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.Image.Input("image"), - ], - 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( - expr="""{"type":"usd","usd":0.02}""", - ), - ) - - @classmethod - async def execute(cls, image: torch.Tensor) -> IO.NodeOutput: - image_binary = tensor_to_bytesio(image, total_pixels=4096*4096).read() - - files = { - "image": image_binary - } - - response_api = await sync_op( - cls, - ApiEndpoint(path="/proxy/stability/v2beta/stable-image/upscale/fast", method="POST"), - response_model=StabilityStableUltraResponse, - files=files, - content_type="multipart/form-data", - ) - - if response_api.finish_reason != "SUCCESS": - raise Exception(f"Stability Upscale Fast failed: {response_api.finish_reason}.") - - image_data = base64.b64decode(response_api.image) - returned_image = bytesio_to_image_tensor(BytesIO(image_data)) - - return IO.NodeOutput(returned_image) - - -class StabilityTextToAudio(IO.ComfyNode): - """Generates high-quality music and sound effects from text descriptions.""" - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityTextToAudio", - display_name="Stability AI Text To Audio", - category="partner/audio/Stability AI", - essentials_category="Audio", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.Combo.Input( - "model", - options=["stable-audio-2.5"], - ), - IO.String.Input("prompt", multiline=True, default=""), - IO.Int.Input( - "duration", - default=190, - min=1, - max=190, - step=1, - tooltip="Controls the duration in seconds of the generated audio.", - optional=True, - ), - IO.Int.Input( - "seed", - default=0, - min=0, - max=4294967294, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="The random seed used for generation.", - optional=True, - ), - IO.Int.Input( - "steps", - default=8, - min=4, - max=8, - step=1, - tooltip="Controls the number of sampling steps.", - optional=True, - advanced=True, - ), - ], - outputs=[ - IO.Audio.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( - expr="""{"type":"usd","usd":0.2}""", - ), - ) - - @classmethod - async def execute(cls, model: str, prompt: str, duration: int, seed: int, steps: int) -> IO.NodeOutput: - validate_string(prompt, max_length=10000) - payload = StabilityTextToAudioRequest(prompt=prompt, model=model, duration=duration, seed=seed, steps=steps) - response_api = await sync_op( - cls, - ApiEndpoint(path="/proxy/stability/v2beta/audio/stable-audio-2/text-to-audio", method="POST"), - response_model=StabilityAudioResponse, - data=payload, - content_type="multipart/form-data", - ) - if not response_api.audio: - raise ValueError("No audio file was received in response.") - return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio))) - - -class StabilityAudioToAudio(IO.ComfyNode): - """Transforms existing audio samples into new high-quality compositions using text instructions.""" - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityAudioToAudio", - display_name="Stability AI Audio To Audio", - category="partner/audio/Stability AI", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.Combo.Input( - "model", - options=["stable-audio-2.5"], - ), - IO.String.Input("prompt", multiline=True, default=""), - IO.Audio.Input("audio", tooltip="Audio must be between 6 and 190 seconds long."), - IO.Int.Input( - "duration", - default=190, - min=1, - max=190, - step=1, - tooltip="Controls the duration in seconds of the generated audio.", - optional=True, - ), - IO.Int.Input( - "seed", - default=0, - min=0, - max=4294967294, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="The random seed used for generation.", - optional=True, - ), - IO.Int.Input( - "steps", - default=8, - min=4, - max=8, - step=1, - tooltip="Controls the number of sampling steps.", - optional=True, - advanced=True, - ), - IO.Float.Input( - "strength", - default=1, - min=0.01, - max=1.0, - step=0.01, - display_mode=IO.NumberDisplay.slider, - tooltip="Parameter controls how much influence the audio parameter has on the generated audio.", - optional=True, - ), - ], - outputs=[ - IO.Audio.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( - expr="""{"type":"usd","usd":0.2}""", - ), - ) - - @classmethod - async def execute( - cls, model: str, prompt: str, audio: Input.Audio, duration: int, seed: int, steps: int, strength: float - ) -> IO.NodeOutput: - validate_string(prompt, max_length=10000) - validate_audio_duration(audio, 6, 190) - payload = StabilityAudioToAudioRequest( - prompt=prompt, model=model, duration=duration, seed=seed, steps=steps, strength=strength - ) - response_api = await sync_op( - cls, - ApiEndpoint(path="/proxy/stability/v2beta/audio/stable-audio-2/audio-to-audio", method="POST"), - response_model=StabilityAudioResponse, - data=payload, - content_type="multipart/form-data", - files={"audio": audio_input_to_mp3(audio)}, - ) - if not response_api.audio: - raise ValueError("No audio file was received in response.") - return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio))) - - -class StabilityAudioInpaint(IO.ComfyNode): - """Transforms part of existing audio sample using text instructions.""" - - @classmethod - def define_schema(cls): - return IO.Schema( - node_id="StabilityAudioInpaint", - display_name="Stability AI Audio Inpaint", - category="partner/audio/Stability AI", - description=cleandoc(cls.__doc__ or ""), - inputs=[ - IO.Combo.Input( - "model", - options=["stable-audio-2.5"], - ), - IO.String.Input("prompt", multiline=True, default=""), - IO.Audio.Input("audio", tooltip="Audio must be between 6 and 190 seconds long."), - IO.Int.Input( - "duration", - default=190, - min=1, - max=190, - step=1, - tooltip="Controls the duration in seconds of the generated audio.", - optional=True, - ), - IO.Int.Input( - "seed", - default=0, - min=0, - max=4294967294, - step=1, - display_mode=IO.NumberDisplay.number, - control_after_generate=True, - tooltip="The random seed used for generation.", - optional=True, - ), - IO.Int.Input( - "steps", - default=8, - min=4, - max=8, - step=1, - tooltip="Controls the number of sampling steps.", - optional=True, - advanced=True, - ), - IO.Int.Input( - "mask_start", - default=30, - min=0, - max=190, - step=1, - optional=True, - advanced=True, - ), - IO.Int.Input( - "mask_end", - default=190, - min=0, - max=190, - step=1, - optional=True, - advanced=True, - ), - ], - outputs=[ - IO.Audio.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( - expr="""{"type":"usd","usd":0.2}""", - ), - ) - - @classmethod - async def execute( - cls, - model: str, - prompt: str, - audio: Input.Audio, - duration: int, - seed: int, - steps: int, - mask_start: int, - mask_end: int, - ) -> IO.NodeOutput: - validate_string(prompt, max_length=10000) - if mask_end <= mask_start: - raise ValueError(f"Value of mask_end({mask_end}) should be greater then mask_start({mask_start})") - validate_audio_duration(audio, 6, 190) - - payload = StabilityAudioInpaintRequest( - prompt=prompt, - model=model, - duration=duration, - seed=seed, - steps=steps, - mask_start=mask_start, - mask_end=mask_end, - ) - response_api = await sync_op( - cls, - endpoint=ApiEndpoint(path="/proxy/stability/v2beta/audio/stable-audio-2/inpaint", method="POST"), - response_model=StabilityAudioResponse, - data=payload, - content_type="multipart/form-data", - files={"audio": audio_input_to_mp3(audio)}, - ) - if not response_api.audio: - raise ValueError("No audio file was received in response.") - return IO.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio))) - - -class StabilityExtension(ComfyExtension): - @override - async def get_node_list(self) -> list[type[IO.ComfyNode]]: - return [ - StabilityStableImageUltraNode, - StabilityStableImageSD_3_5Node, - StabilityUpscaleConservativeNode, - StabilityUpscaleCreativeNode, - StabilityUpscaleFastNode, - StabilityTextToAudio, - StabilityAudioToAudio, - StabilityAudioInpaint, - ] - - -async def comfy_entrypoint() -> StabilityExtension: - return StabilityExtension() diff --git a/comfy_api_nodes/util/__init__.py b/comfy_api_nodes/util/__init__.py index 25cb88869..1fb6b96cf 100644 --- a/comfy_api_nodes/util/__init__.py +++ b/comfy_api_nodes/util/__init__.py @@ -26,6 +26,7 @@ from .conversions import ( text_filepath_to_base64_string, text_filepath_to_data_uri, trim_video, + upscale_image_tensor_to_min_pixels, upscale_video_to_min_pixels, video_to_base64_string, ) @@ -99,6 +100,7 @@ __all__ = [ "text_filepath_to_base64_string", "text_filepath_to_data_uri", "trim_video", + "upscale_image_tensor_to_min_pixels", "upscale_video_to_min_pixels", "video_to_base64_string", # Validation utilities diff --git a/comfy_api_nodes/util/conversions.py b/comfy_api_nodes/util/conversions.py index a1b5d599c..9cd644fc0 100644 --- a/comfy_api_nodes/util/conversions.py +++ b/comfy_api_nodes/util/conversions.py @@ -448,6 +448,15 @@ def _compute_upscale_dims(src_w: int, src_h: int, total_pixels: int) -> tuple[in return new_w, new_h +def upscale_image_tensor_to_min_pixels(image: torch.Tensor, total_pixels: int) -> torch.Tensor: + samples = image.movedim(-1, 1) + dims = _compute_upscale_dims(samples.shape[3], samples.shape[2], int(total_pixels)) + if dims is None: + return image + new_w, new_h = dims + return common_upscale(samples, new_w, new_h, "lanczos", "disabled").movedim(1, -1) + + def upscale_video_to_min_pixels(video: Input.Video, min_pixels: int) -> Input.Video: """Upscale a video to meet at least ``min_pixels`` (w * h), preserving aspect ratio. diff --git a/requirements.txt b/requirements.txt index 1d9fe4137..34af2ce39 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,5 @@ comfyui-frontend-package==1.45.20 -comfyui-workflow-templates==0.11.1 +comfyui-workflow-templates==0.11.2 comfyui-embedded-docs==0.5.6 torch torchsde