mirror of
https://github.com/Comfy-Org/ComfyUI_frontend.git
synced 2026-03-12 00:20:15 +00:00
1.40.9 (#9034)
Patch version increment to 1.40.9 **Base branch:** `main` ┆Issue is synchronized with this [Notion page](https://www.notion.so/PR-9034-1-40-9-30e6d73d365081a1b1e4e7a1c0b77629) by [Unito](https://www.unito.io) --------- Co-authored-by: christian-byrne <72887196+christian-byrne@users.noreply.github.com> Co-authored-by: github-actions <github-actions@github.com> Co-authored-by: Alexander Brown <drjkl@comfy.org>
This commit is contained in:
Comfy Org PR Bot
@@ -2305,6 +2305,304 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsAudioIsolation": {
|
||||
"display_name": "ElevenLabs Voice Isolation",
|
||||
"description": "Remove background noise from audio, isolating vocals or speech.",
|
||||
"inputs": {
|
||||
"audio": {
|
||||
"name": "audio",
|
||||
"tooltip": "Audio to process for background noise removal."
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsInstantVoiceClone": {
|
||||
"display_name": "ElevenLabs Instant Voice Clone",
|
||||
"description": "Create a cloned voice from audio samples. Provide 1-8 audio recordings of the voice to clone.",
|
||||
"inputs": {
|
||||
"files": {
|
||||
"name": "files",
|
||||
"tooltip": "Audio recordings for voice cloning."
|
||||
},
|
||||
"remove_background_noise": {
|
||||
"name": "remove_background_noise",
|
||||
"tooltip": "Remove background noise from voice samples using audio isolation."
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"name": "voice",
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsSpeechToSpeech": {
|
||||
"display_name": "ElevenLabs Speech to Speech",
|
||||
"description": "Transform speech from one voice to another while preserving the original content and emotion.",
|
||||
"inputs": {
|
||||
"voice": {
|
||||
"name": "voice",
|
||||
"tooltip": "Target voice for the transformation. Connect from Voice Selector or Instant Voice Clone."
|
||||
},
|
||||
"audio": {
|
||||
"name": "audio",
|
||||
"tooltip": "Source audio to transform."
|
||||
},
|
||||
"stability": {
|
||||
"name": "stability",
|
||||
"tooltip": "Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech."
|
||||
},
|
||||
"model": {
|
||||
"name": "model",
|
||||
"tooltip": "Model to use for speech-to-speech transformation."
|
||||
},
|
||||
"output_format": {
|
||||
"name": "output_format",
|
||||
"tooltip": "Audio output format."
|
||||
},
|
||||
"seed": {
|
||||
"name": "seed",
|
||||
"tooltip": "Seed for reproducibility."
|
||||
},
|
||||
"remove_background_noise": {
|
||||
"name": "remove_background_noise",
|
||||
"tooltip": "Remove background noise from input audio using audio isolation."
|
||||
},
|
||||
"control_after_generate": {
|
||||
"name": "control after generate"
|
||||
},
|
||||
"model_similarity_boost": {
|
||||
"name": "similarity_boost"
|
||||
},
|
||||
"model_speed": {
|
||||
"name": "speed"
|
||||
},
|
||||
"model_style": {
|
||||
"name": "style"
|
||||
},
|
||||
"model_use_speaker_boost": {
|
||||
"name": "use_speaker_boost"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsSpeechToText": {
|
||||
"display_name": "ElevenLabs Speech to Text",
|
||||
"description": "Transcribe audio to text. Supports automatic language detection, speaker diarization, and audio event tagging.",
|
||||
"inputs": {
|
||||
"audio": {
|
||||
"name": "audio",
|
||||
"tooltip": "Audio to transcribe."
|
||||
},
|
||||
"model": {
|
||||
"name": "model",
|
||||
"tooltip": "Model to use for transcription."
|
||||
},
|
||||
"language_code": {
|
||||
"name": "language_code",
|
||||
"tooltip": "ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection."
|
||||
},
|
||||
"num_speakers": {
|
||||
"name": "num_speakers",
|
||||
"tooltip": "Maximum number of speakers to predict. Set to 0 for automatic detection."
|
||||
},
|
||||
"seed": {
|
||||
"name": "seed",
|
||||
"tooltip": "Seed for reproducibility (determinism not guaranteed)."
|
||||
},
|
||||
"control_after_generate": {
|
||||
"name": "control after generate"
|
||||
},
|
||||
"model_diarization_threshold": {
|
||||
"name": "diarization_threshold"
|
||||
},
|
||||
"model_diarize": {
|
||||
"name": "diarize"
|
||||
},
|
||||
"model_tag_audio_events": {
|
||||
"name": "tag_audio_events"
|
||||
},
|
||||
"model_temperature": {
|
||||
"name": "temperature"
|
||||
},
|
||||
"model_timestamps_granularity": {
|
||||
"name": "timestamps_granularity"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"name": "text",
|
||||
"tooltip": null
|
||||
},
|
||||
"1": {
|
||||
"name": "language_code",
|
||||
"tooltip": null
|
||||
},
|
||||
"2": {
|
||||
"name": "words_json",
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsTextToDialogue": {
|
||||
"display_name": "ElevenLabs Text to Dialogue",
|
||||
"description": "Generate multi-speaker dialogue from text. Each dialogue entry has its own text and voice.",
|
||||
"inputs": {
|
||||
"stability": {
|
||||
"name": "stability",
|
||||
"tooltip": "Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech."
|
||||
},
|
||||
"apply_text_normalization": {
|
||||
"name": "apply_text_normalization",
|
||||
"tooltip": "Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it."
|
||||
},
|
||||
"model": {
|
||||
"name": "model",
|
||||
"tooltip": "Model to use for dialogue generation."
|
||||
},
|
||||
"inputs": {
|
||||
"name": "inputs",
|
||||
"tooltip": "Number of dialogue entries."
|
||||
},
|
||||
"language_code": {
|
||||
"name": "language_code",
|
||||
"tooltip": "ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection."
|
||||
},
|
||||
"seed": {
|
||||
"name": "seed",
|
||||
"tooltip": "Seed for reproducibility."
|
||||
},
|
||||
"output_format": {
|
||||
"name": "output_format",
|
||||
"tooltip": "Audio output format."
|
||||
},
|
||||
"control_after_generate": {
|
||||
"name": "control after generate"
|
||||
},
|
||||
"inputs_text1": {
|
||||
"name": "text1"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsTextToSoundEffects": {
|
||||
"display_name": "ElevenLabs Text to Sound Effects",
|
||||
"description": "Generate sound effects from text descriptions.",
|
||||
"inputs": {
|
||||
"text": {
|
||||
"name": "text",
|
||||
"tooltip": "Text description of the sound effect to generate."
|
||||
},
|
||||
"model": {
|
||||
"name": "model",
|
||||
"tooltip": "Model to use for sound effect generation."
|
||||
},
|
||||
"output_format": {
|
||||
"name": "output_format",
|
||||
"tooltip": "Audio output format."
|
||||
},
|
||||
"model_duration": {
|
||||
"name": "duration"
|
||||
},
|
||||
"model_loop": {
|
||||
"name": "loop"
|
||||
},
|
||||
"model_prompt_influence": {
|
||||
"name": "prompt_influence"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsTextToSpeech": {
|
||||
"display_name": "ElevenLabs Text to Speech",
|
||||
"description": "Convert text to speech.",
|
||||
"inputs": {
|
||||
"voice": {
|
||||
"name": "voice",
|
||||
"tooltip": "Voice to use for speech synthesis. Connect from Voice Selector or Instant Voice Clone."
|
||||
},
|
||||
"text": {
|
||||
"name": "text",
|
||||
"tooltip": "The text to convert to speech."
|
||||
},
|
||||
"stability": {
|
||||
"name": "stability",
|
||||
"tooltip": "Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech."
|
||||
},
|
||||
"apply_text_normalization": {
|
||||
"name": "apply_text_normalization",
|
||||
"tooltip": "Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it."
|
||||
},
|
||||
"model": {
|
||||
"name": "model",
|
||||
"tooltip": "Model to use for text-to-speech."
|
||||
},
|
||||
"language_code": {
|
||||
"name": "language_code",
|
||||
"tooltip": "ISO-639-1 or ISO-639-3 language code (e.g., 'en', 'es', 'fra'). Leave empty for automatic detection."
|
||||
},
|
||||
"seed": {
|
||||
"name": "seed",
|
||||
"tooltip": "Seed for reproducibility (determinism not guaranteed)."
|
||||
},
|
||||
"output_format": {
|
||||
"name": "output_format",
|
||||
"tooltip": "Audio output format."
|
||||
},
|
||||
"control_after_generate": {
|
||||
"name": "control after generate"
|
||||
},
|
||||
"model_similarity_boost": {
|
||||
"name": "similarity_boost"
|
||||
},
|
||||
"model_speed": {
|
||||
"name": "speed"
|
||||
},
|
||||
"model_style": {
|
||||
"name": "style"
|
||||
},
|
||||
"model_use_speaker_boost": {
|
||||
"name": "use_speaker_boost"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"ElevenLabsVoiceSelector": {
|
||||
"display_name": "ElevenLabs Voice Selector",
|
||||
"description": "Select a predefined ElevenLabs voice for text-to-speech generation.",
|
||||
"inputs": {
|
||||
"voice": {
|
||||
"name": "voice",
|
||||
"tooltip": "Choose a voice from the predefined ElevenLabs voices."
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"name": "voice",
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"EmptyAceStep1_5LatentAudio": {
|
||||
"display_name": "Empty Ace Step 1.5 Latent Audio",
|
||||
"inputs": {
|
||||
@@ -3519,6 +3817,50 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"GLSLShader": {
|
||||
"display_name": "GLSL Shader",
|
||||
"description": "Apply GLSL ES fragment shaders to images. u_resolution (vec2) is always available.",
|
||||
"inputs": {
|
||||
"fragment_shader": {
|
||||
"name": "fragment_shader",
|
||||
"tooltip": "GLSL fragment shader source code (GLSL ES 3.00 / WebGL 2.0 compatible)"
|
||||
},
|
||||
"size_mode": {
|
||||
"name": "size_mode",
|
||||
"tooltip": "Output size: 'from_input' uses first input image dimensions, 'custom' allows manual size"
|
||||
},
|
||||
"images": {
|
||||
"name": "images",
|
||||
"tooltip": "Images are available as u_image0-4 (sampler2D) in the shader code"
|
||||
},
|
||||
"floats": {
|
||||
"name": "floats",
|
||||
"tooltip": "Floats are available as u_float0-4 in the shader code"
|
||||
},
|
||||
"ints": {
|
||||
"name": "ints",
|
||||
"tooltip": "Ints are available as u_int0-4 in the shader code"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"name": "IMAGE0",
|
||||
"tooltip": "Available via layout(location = 0) out vec4 fragColor0 in the shader code"
|
||||
},
|
||||
"1": {
|
||||
"name": "IMAGE1",
|
||||
"tooltip": "Available via layout(location = 1) out vec4 fragColor1 in the shader code"
|
||||
},
|
||||
"2": {
|
||||
"name": "IMAGE2",
|
||||
"tooltip": "Available via layout(location = 2) out vec4 fragColor2 in the shader code"
|
||||
},
|
||||
"3": {
|
||||
"name": "IMAGE3",
|
||||
"tooltip": "Available via layout(location = 3) out vec4 fragColor3 in the shader code"
|
||||
}
|
||||
}
|
||||
},
|
||||
"GrokImageEditNode": {
|
||||
"display_name": "Grok Image Edit",
|
||||
"description": "Modify an existing image based on a text prompt",
|
||||
@@ -14723,6 +15065,94 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"TextGenerate": {
|
||||
"display_name": "TextGenerate",
|
||||
"inputs": {
|
||||
"clip": {
|
||||
"name": "clip"
|
||||
},
|
||||
"prompt": {
|
||||
"name": "prompt"
|
||||
},
|
||||
"max_length": {
|
||||
"name": "max_length"
|
||||
},
|
||||
"sampling_mode": {
|
||||
"name": "sampling_mode"
|
||||
},
|
||||
"image": {
|
||||
"name": "image"
|
||||
},
|
||||
"sampling_mode_min_p": {
|
||||
"name": "min_p"
|
||||
},
|
||||
"sampling_mode_repetition_penalty": {
|
||||
"name": "repetition_penalty"
|
||||
},
|
||||
"sampling_mode_seed": {
|
||||
"name": "seed"
|
||||
},
|
||||
"sampling_mode_temperature": {
|
||||
"name": "temperature"
|
||||
},
|
||||
"sampling_mode_top_k": {
|
||||
"name": "top_k"
|
||||
},
|
||||
"sampling_mode_top_p": {
|
||||
"name": "top_p"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"name": "generated_text",
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"TextGenerateLTX2Prompt": {
|
||||
"display_name": "TextGenerateLTX2Prompt",
|
||||
"inputs": {
|
||||
"clip": {
|
||||
"name": "clip"
|
||||
},
|
||||
"prompt": {
|
||||
"name": "prompt"
|
||||
},
|
||||
"max_length": {
|
||||
"name": "max_length"
|
||||
},
|
||||
"sampling_mode": {
|
||||
"name": "sampling_mode"
|
||||
},
|
||||
"image": {
|
||||
"name": "image"
|
||||
},
|
||||
"sampling_mode_min_p": {
|
||||
"name": "min_p"
|
||||
},
|
||||
"sampling_mode_repetition_penalty": {
|
||||
"name": "repetition_penalty"
|
||||
},
|
||||
"sampling_mode_seed": {
|
||||
"name": "seed"
|
||||
},
|
||||
"sampling_mode_temperature": {
|
||||
"name": "temperature"
|
||||
},
|
||||
"sampling_mode_top_k": {
|
||||
"name": "top_k"
|
||||
},
|
||||
"sampling_mode_top_p": {
|
||||
"name": "top_p"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"0": {
|
||||
"name": "generated_text",
|
||||
"tooltip": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"TextToLowercase": {
|
||||
"display_name": "Text to Lowercase",
|
||||
"inputs": {
|
||||
|
||||
Reference in New Issue
Block a user