Files
songforge/core/workflow.py
T
2026-10-09 19:18:33 +08:00

208 lines
8.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""songforge 核心包 - 工作流构建器"""
import copy
import json
import os
import re
from .errors import ConfigError
ROOT = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
# UI widgets_values 顺序 -> API inputs 键名。按节点类型分别声明,避免混用。
WIDGET_MAP = {
"CheckpointLoaderSimple": ["ckpt_name"],
"LoraLoader": ["lora_name", "strength_model", "strength_clip"],
"ModelSamplingAuraFlow": ["shift", "sampling"],
"EmptyAceStep1.5LatentAudio": ["seconds", "batch_size"],
"TextEncodeAceStepAudio1.5": [
"tags", "lyrics", "seed", "bpm", "duration", "timesignature",
"language", "keyscale", "generate_audio_codes", "cfg_scale",
"temperature", "top_p", "top_k", "min_p",
],
"KSampler": ["seed", "control_after_generate", "steps", "cfg",
"sampler_name", "scheduler", "denoise"],
"SaveAudio": ["filename_prefix"],
"SaveAudioAdvanced": ["filename_prefix", "format"],
"VAEDecodeAudio": [],
}
def load_template(path_or_name):
"""path_or_name 可以是 workflows 下的文件名,也可以是绝对路径。"""
p = path_or_name
if not os.path.isabs(p):
p = os.path.join(ROOT, p)
if not os.path.exists(p):
raise ConfigError("workflow 模板不存在: %s" % p)
with open(p, encoding="utf-8") as f:
return json.load(f)
def convert(ui_wf):
"""UI 格式 workflow dict -> API prompt dict。"""
links = ui_wf["links"]
# 兼容两种格式:ComfyUI 对象数组 (dict) 或 元组列表 [id, origin, target, ...]
if links and isinstance(links[0], dict):
link_src = {l["id"]: [l["origin_id"], l["origin_slot"]] for l in links}
else:
link_src = {l[0]: [l[1], l[2]] for l in links}
api = {}
for n in ui_wf["nodes"]:
cls = n["type"]
keys = WIDGET_MAP.get(cls)
inputs = {}
if keys:
wv = n.get("widgets_values", [])
if len(wv) < len(keys):
raise ConfigError(
"节点 %s (%s) 的 widgets_values 只有 %d 项,期望 %d 项;"
"模板可能被手改过"
% (n.get("id"), cls, len(wv), len(keys)))
for k, v in zip(keys, wv):
inputs[k] = v
for inp in n.get("inputs", []):
lid = inp.get("link")
if lid is not None and lid in link_src:
src = link_src[lid]
inputs[inp["name"]] = [str(src[0]), src[1]]
api[str(n["id"])] = {"class_type": cls, "inputs": inputs}
return api
def find_node(ui_wf, class_type):
for n in ui_wf["nodes"]:
if n["type"] == class_type:
return n
return None
def render(wf_result):
"""build_workflow 返回的 dict -> API prompt。"""
if isinstance(wf_result, dict) and "workflow" in wf_result and "class_type" not in wf_result:
return convert(wf_result["workflow"])
return convert(wf_result)
def build_workflow(template, *, title, tags, lyrics, seed, bpm, duration,
keyscale, sampler, encode, model, output_prefix,
output_format, language="zh", timesignature="4"):
"""按节点类型定位并写入参数。不依赖固定节点 ID。
model["lora"] 为空 / None 时直接跳过 LoraLoader:
我们用的 ace_step_1.5_turbo_swl_fused.safetensors 本身就是
"""
from ..config.loader import load
from ..rules.ironlaw import build_tags as _build_tags, build_lyrics, validate
from ..rules.ironlaw import build_chill_lyrics
# 1. 解析歌词章节
sections = []
lines = lyrics.split('\n')
current_tag = None
current_content = []
for line in lines:
line = line.strip()
if not line:
continue
tag_match = re.match(r'^\[(\w+(?:[-]\w+)?)\]$', line)
if tag_match:
if current_tag is not None and current_content:
sections.append((current_tag, '\n'.join(current_content)))
current_tag = tag_match.group(1)
current_content = []
else:
if current_tag is not None:
current_content.append(line)
if current_tag is not None and current_content:
sections.append((current_tag, '\n'.join(current_content)))
has_intro = lyrics.lstrip().lower().startswith('[intro]')
# 5. 组合工作流
workflow = copy.deepcopy(template)
# 从配置文件加载默认参数(single source of truth)
config = load()
model_cfg = config.get("model", {})
sampler_cfg = config.get("sampler", {})
encode_cfg = config.get("encode", {})
paths_cfg = config.get("paths", {})
# 合并参数来源: CLI/函数传入 > config > 硬coded 安全兜底
ckpt_name = model.get("checkpoint") or model_cfg.get("checkpoint", "ace_step_1.5_turbo_swl_fused.safetensors")
lora_name = model.get("lora") or model_cfg.get("lora", "")
lora_model_strength = model.get("lora_model_strength", model_cfg.get("lora_model_strength", 0.5))
lora_clip_strength = model.get("lora_clip_strength", model_cfg.get("lora_clip_strength", 0.5))
shift = sampler.get("shift", sampler_cfg.get("shift", 5.5))
sampling = sampler.get("sampling", sampler_cfg.get("sampling", "flow"))
steps = sampler.get("steps", sampler_cfg.get("steps", 28))
cfg = sampler.get("cfg", sampler_cfg.get("cfg", 2.0))
sampler_name = sampler.get("sampler_name", sampler_cfg.get("sampler_name", "euler"))
scheduler = sampler.get("scheduler", sampler_cfg.get("scheduler", "simple"))
denoise = sampler.get("denoise", sampler_cfg.get("denoise", 1.0))
batch_size = sampler.get("batch_size", sampler_cfg.get("batch_size", 1))
cfg_scale = encode.get("cfg_scale", encode_cfg.get("cfg_scale", 3.0))
temperature = encode.get("temperature", encode_cfg.get("temperature", 0.68))
top_p = encode.get("top_p", encode_cfg.get("top_p", 0.88))
top_k = encode.get("top_k", encode_cfg.get("top_k", 50))
min_p = encode.get("min_p", encode_cfg.get("min_p", 0.02))
generate_audio_codes = encode.get("generate_audio_codes", encode_cfg.get("generate_audio_codes", True))
output_format = output_format or paths_cfg.get("output_format", "flac")
# 遍历节点设置参数
for n in workflow["nodes"]:
if n["type"] == "CheckpointLoaderSimple":
n["widgets_values"] = [ckpt_name]
elif n["type"] == "LoraLoader":
# 设置 LoRA 加载器参数
if "widgets_values" in n:
n["widgets_values"] = [lora_name, lora_model_strength, lora_clip_strength]
elif n["type"] == "ModelSamplingAuraFlow":
if "widgets_values" in n:
n["widgets_values"] = [shift, sampling]
elif n["type"] == "EmptyAceStep1.5LatentAudio":
if "widgets_values" in n:
n["widgets_values"] = [duration, batch_size]
elif n["type"] == "TextEncodeAceStepAudio1.5":
if "widgets_values" in n:
# 构建 widgets_values: tags, lyrics, seed, bpm, duration, timesignature,
# language, keyscale, generate_audio_codes, cfg_scale, temperature, top_p, top_k, min_p
n["widgets_values"] = [
tags,
lyrics,
seed,
bpm,
duration,
timesignature,
language,
keyscale,
generate_audio_codes,
cfg_scale,
temperature,
top_p,
top_k,
min_p,
]
elif n["type"] == "KSampler":
if "widgets_values" in n:
n["widgets_values"] = [seed, "fixed", steps, cfg,
sampler_name, scheduler, denoise]
elif n["type"] == "SaveAudioAdvanced":
if "widgets_values" in n:
n["widgets_values"] = [output_prefix, output_format]
elif n["type"] == "SaveAudio":
if "widgets_values" in n:
n["widgets_values"] = [output_prefix]
return {
"success": True,
"workflow": workflow,
"lyrics": lyrics,
"tags": tags,
"has_intro": has_intro,
}