nodes/gateway-ComfyUI-Kie-API
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: split suno nodes and update readme

Browse Source
This commit is contained in:
Dreaming Computers
2026-02-01 15:05:32 +07:00
parent ff73c25178
commit ff2e2adc34
5 changed files with 158 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+28 -31
View File
@@ -37,51 +37,48 @@ Do **NOT** share your API key or commit it to version control.
This node pack currently includes the following nodes:
### Generation Nodes
## Image Nodes
- **Nano Banana Pro Image**
- Image generation node using the Googles Nano Banana Pro model
- **Seedream Text-to-Image / Edit**
- Text-to-image and image-editing node for Seedream models.
- Supports prompt-based generation and edits.
- **Flux 2 Image-to-Image (Pro/Flex)**
- Image-to-image node with a model dropdown for Pro or Flex.
- Accepts 1–8 input images via ComfyUI batch.
## Video Nodes
- **Kling 2.6 Image-to-Video**
- Generates video from a single input image.
- Uses the Kling 2.6 image-to-video model.
- **Kling 2.5 I2V Pro**
- Generates video from a required first image and optional tail image.
- Uses the Kling 2.5 Turbo image-to-video Pro model.
- **Kling 2.6 Text-to-Video**
- Generates video directly from a text prompt.
- Supports aspect ratio, duration, and sound options as exposed by the API.
- **Kling 2.6 Motion-Control Image-to-Video**
- Image-to-video generation with additional motion control parameters.
- Designed for more directed camera and motion behavior.
- **Seedance V1 Pro (Fast) Image-to-Video**
Fast image-to-video generation optimized for quick iteration.
- **Seedance 1.5 Pro Image-to-Video, Text-to-Video**
Higher-quality image-to-video generation using the Seedance 1.5 Pro model.
## LLM Nodes
- **Gemini (LLM) [Experimental]**
- Text generation node using Gemini 2.5/3 Pro/Flash chat completions.
- Supports role selection, media inputs (images/video/audio), optional reasoning output, and Google Search toggle.
- **Suno Music (Generate)**
- Generates music and returns AUDIO output.
- Uses KIE Suno API `generate` + `record-info` polling.
## Audio Nodes
- **Suno Music (Basic)**
- Minimal inputs: title, style, prompt, model, instrument, tags, gender.
- Returns AUDIO output via KIE Suno API `generate` + `record-info` polling.
- **Suno Music (Advanced)**
- Adds style/creative weights to the Basic node.
- Returns AUDIO output via KIE Suno API `generate` + `record-info` polling.
- **Kling 2.6 Image-to-Video**
- Generates video from a single input image.
- Uses the Kling 2.6 image-to-video model.
- **Kling 2.5 I2V Pro**
- Generates video from a required first image and optional tail image.
- Uses the Kling 2.5 Turbo image-to-video Pro model.
- **Kling 2.6 Text-to-Video**
- Generates video directly from a text prompt.
- Supports aspect ratio, duration, and sound options as exposed by the API.
- **Kling 2.6 Motion-Control Image-to-Video**
- Image-to-video generation with additional motion control parameters.
- Designed for more directed camera and motion behavior.
- **Seedance V1 Pro (Fast) Image-to-Video**
Fast image-to-video generation optimized for quick iteration.
- **Seedance 1.5 Pro Image-to-Video, Text-to-Video**
Higher-quality image-to-video generation using the Seedance 1.5 Pro model.
### Utility / Helper Nodes
## Utility / Helper Nodes
- **Get Remaining Credits**
- Return number of credits remaining
kie_api/suno_music.py
+12
View File
@@ -264,6 +264,18 @@ def run_suno_generate(
raise RuntimeError(f"Failed to download audio: {exc}") from exc
audio_output = _audio_bytes_to_comfy_audio(audio_bytes, "audio.mp3")
try:
import torch
waveform = audio_output.get("waveform")
if not isinstance(waveform, torch.Tensor):
waveform = torch.as_tensor(waveform)
if waveform.ndim == 1:
waveform = waveform.unsqueeze(0)
if waveform.ndim == 2:
waveform = waveform.unsqueeze(0)
audio_output["waveform"] = waveform
except Exception as exc:
raise RuntimeError(f"Failed to normalize audio waveform for ComfyUI: {exc}") from exc
if log:
waveform = audio_output.get("waveform")
shape = getattr(waveform, "shape", None)
nodes.py
+89 -12
View File
@@ -723,11 +723,11 @@ Outputs:
return (content, reasoning, raw_json)
class KIE_Suno_Music:
class KIE_Suno_Music_Basic:
HELP = """
KIE Suno Music (Generate)
KIE Suno Music (Basic)
Create a Suno music generation task via KIE API. Returns a taskId.
Create a Suno music generation task via KIE API. Returns an AUDIO output and record JSON.
Inputs:
- title: Track title (required in custom mode)
@@ -736,14 +736,13 @@ Inputs:
- custom_mode: Enable custom mode (required)
- instrumental: Instrumental-only mode (required)
- model: V4 / V4_5 / V4_5PLUS / V4_5ALL / V5
- style: Required in custom mode
- title: Required in custom mode
Optional:
- negative_tags: Optional tags to avoid
- vocal_gender: m or f (custom mode only)
- style_weight / weirdness_constraint / audio_weight: 0..1
- log: Console logging on/off
Outputs:
Outputs:
- AUDIO: Generated audio
- STRING: raw_json
"""
@@ -761,7 +760,82 @@ Inputs:
},
"optional": {
"negative_tags": ("STRING", {"default": ""}),
"vocal_gender": ("COMBO", {"options": ["m", "f"], "default": "m"}),
"vocal_gender": ("COMBO", {"options": ["male", "female"], "default": "male"}),
"log": ("BOOLEAN", {"default": True}),
},
}
RETURN_TYPES = ("AUDIO", "STRING")
RETURN_NAMES = ("audio", "raw_json")
FUNCTION = "generate"
CATEGORY = "kie/api"
def generate(
self,
title: str,
style: str,
prompt: str,
custom_mode: bool,
instrumental: bool,
model: str,
negative_tags: str = "",
vocal_gender: str = "male",
log: bool = True,
):
gender_value = "m" if vocal_gender == "male" else "f"
audio_output, raw_json = run_suno_generate(
prompt=prompt,
custom_mode=custom_mode,
instrumental=instrumental,
model=model,
style=style,
title=title,
negative_tags=negative_tags,
vocal_gender=gender_value,
log=log,
)
return (audio_output, raw_json)
class KIE_Suno_Music_Advanced:
HELP = """
KIE Suno Music (Advanced)
Create a Suno music generation task via KIE API. Returns an AUDIO output and record JSON.
Inputs:
- title: Track title (required in custom mode)
- style: Style text (required in custom mode)
- prompt: Text prompt (lyrics in custom mode when instrumental is false)
- custom_mode: Enable custom mode (required)
- instrumental: Instrumental-only mode (required)
- model: V4 / V4_5 / V4_5PLUS / V4_5ALL / V5
Optional:
- negative_tags: Optional tags to avoid
- vocal_gender: m or f (custom mode only)
- style_weight / weirdness_constraint / audio_weight: 0..1
- log: Console logging on/off
Outputs:
- AUDIO: Generated audio
- STRING: raw_json
"""
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"title": ("STRING", {"default": ""}),
"style": ("STRING", {"default": "", "multiline": True}),
"prompt": ("STRING", {"multiline": True}),
"custom_mode": ("BOOLEAN", {"default": True}),
"instrumental": ("BOOLEAN", {"default": True}),
"model": ("COMBO", {"options": SUNO_MODEL_OPTIONS, "default": "V4_5"}),
},
"optional": {
"negative_tags": ("STRING", {"default": ""}),
"vocal_gender": ("COMBO", {"options": ["male", "female"], "default": "male"}),
"style_weight": ("FLOAT", {"default": 0.65, "min": 0.0, "max": 1.0, "step": 0.01}),
"weirdness_constraint": ("FLOAT", {"default": 0.65, "min": 0.0, "max": 1.0, "step": 0.01}),
"audio_weight": ("FLOAT", {"default": 0.65, "min": 0.0, "max": 1.0, "step": 0.01}),
@@ -783,12 +857,13 @@ Inputs:
instrumental: bool,
model: str,
negative_tags: str = "",
vocal_gender: str = "m",
vocal_gender: str = "male",
style_weight: float = 0.65,
weirdness_constraint: float = 0.65,
audio_weight: float = 0.65,
log: bool = True,
):
gender_value = "m" if vocal_gender == "male" else "f"
audio_output, raw_json = run_suno_generate(
prompt=prompt,
custom_mode=custom_mode,
@@ -797,7 +872,7 @@ Inputs:
style=style,
title=title,
negative_tags=negative_tags,
vocal_gender=vocal_gender,
vocal_gender=gender_value,
style_weight=style_weight,
weirdness_constraint=weirdness_constraint,
audio_weight=audio_weight,
@@ -993,7 +1068,8 @@ NODE_CLASS_MAPPINGS = {
"KIE_Kling26Motion_I2V": KIE_Kling26Motion_I2V,
"KIE_Flux2_I2I": KIE_Flux2_I2I,
"KIE_Gemini3Pro_LLM": KIE_Gemini3Pro_LLM,
"KIE_Suno_Music": KIE_Suno_Music,
"KIE_Suno_Music_Basic": KIE_Suno_Music_Basic,
"KIE_Suno_Music_Advanced": KIE_Suno_Music_Advanced,
"KIE_GridSlice": KIE_GridSlice,
"KIEParsePromptGridJSON": KIEParsePromptGridJSON,
}
@@ -1010,7 +1086,8 @@ NODE_DISPLAY_NAME_MAPPINGS = {
"KIE_Kling26Motion_I2V": "KIE Kling 2.6 Motion-Control (I2V)",
"KIE_Flux2_I2I": "KIE Flux 2 (Image-to-Image)",
"KIE_Gemini3Pro_LLM": "KIE Gemini (LLM) [Experimental]",
"KIE_Suno_Music": "KIE Suno Music (Generate)",
"KIE_Suno_Music_Basic": "KIE Suno Music (Basic)",
"KIE_Suno_Music_Advanced": "KIE Suno Music (Advanced)",
"KIE_GridSlice": "KIE Grid Slice",
"KIEParsePromptGridJSON": "KIE Parse Prompt Grid JSON (1..9)",
}
web/docs/KIE_Suno_Music.md → web/docs/KIE_Suno_Music_Advanced.md
+3 -3
View File
@@ -1,6 +1,6 @@
# KIE Suno Music (Generate)
# KIE Suno Music (Advanced)
Create a Suno music generation task via KIE API. This node polls until completion and returns an AUDIO output.
Create a Suno music generation task via KIE API. This node exposes advanced weights and returns an AUDIO output.
## Inputs
- **title** (STRING, required): Track title (required in custom mode).
@@ -11,7 +11,7 @@ Create a Suno music generation task via KIE API. This node polls until completio
- **model** (COMBO, required): `V4`, `V4_5`, `V4_5PLUS`, `V4_5ALL`, `V5`
Optional:
- **negative_tags** (STRING): Optional.
- **vocal_gender** (COMBO): `m` or `f` (custom mode only).
- **vocal_gender** (COMBO): `male` or `female` (custom mode only).
- **style_weight** (FLOAT): 0..1
- **weirdness_constraint** (FLOAT): 0..1
- **audio_weight** (FLOAT): 0..1
web/docs/KIE_Suno_Music_Basic.md
+26
View File
@@ -0,0 +1,26 @@
# KIE Suno Music (Basic)
Create a Suno music generation task via KIE API. This node keeps inputs minimal and returns an AUDIO output.
## Inputs
- **title** (STRING, required): Track title (required in custom mode).
- **style** (STRING, required): Style text (required in custom mode, multiline).
- **prompt** (STRING, required): Prompt text (lyrics in custom mode when instrumental is false).
- **custom_mode** (BOOLEAN, required): Enable custom mode.
- **instrumental** (BOOLEAN, required): Instrumental-only mode.
- **model** (COMBO, required): `V4`, `V4_5`, `V4_5PLUS`, `V4_5ALL`, `V5`
Optional:
- **negative_tags** (STRING): Optional.
- **vocal_gender** (COMBO): `male` or `female` (custom mode only).
- **log** (BOOLEAN): Enable console logging.
## Outputs
- **audio** (AUDIO): Generated audio.
- **raw_json** (STRING): Full API response JSON.
## Notes
- Non-custom mode expects **prompt only** (500 chars max); other fields should be empty.
- Custom mode requirements:
- Instrumental: `style` + `title`
- Non-instrumental: `style` + `title` + `prompt`