ComfyUI Node
MD: ACE-Step XL Loader π΅
π΅ MD: ACE-Step 1.5 XL Loader β Loads XL variants (hidden_size=2560). Tunable AuraFlow shift baked in β no external node needed. Outputs MODEL + sigma plot IMAGE + analytics STRING. Session cache skips 90s reload on re-queue.
MD: ACE-Step XL Loader π΅
- model
- sigma_plot
- analytics
βmodel_path[place XL model folder path here]βΊ
βvariantxl-turboβΊ
βaura_shift3.00βΊ
βdevicecudaβΊ
CategoryMD_Nodes/Loaders
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| model_path | STRING | [place XL model folder path here] | Full path to the XL model directory. Must contain: config.json, modeling_*.py, silence_latent.pt, and weights (.safetensors). Session cache: same path+variant skips the 90s reload on re-queue. |
| variant | COMBO | xl-turbo | xl-turbo : DMD2 distilled, 4β8 steps (fastest) xl-sft : 50-step undistilled, broader manifold (best quality) xl-base : Unaligned research weights |
| aura_shift | FLOAT | 3.000.1β10 | AuraFlow sigma shift β controls denoising schedule curvature. Formula: Ο(t) = t / (t + shift*(1βt)), multiplier=1.0 shift = 1.0 β linear schedule shift = 1.73 β AuraFlow default (β3) shift = 3.0 β ACE-Step XL validated (ByteDance default) shift > 1.0 β front-loads denoising (more aggressive early) Per-variant recommendations: xl-turbo : 3.0 (validated) xl-sft : 2.5 (start here, tune down for coherence) xl-base : 1.73 (AuraFlow default as baseline) No external ModelSamplingAuraFlow node needed β this loader bakes the shift in directly. |
| device | COMBO | cuda | 2 options: cuda, cpu |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| model | MODEL | β |
| sigma_plot | IMAGE | β |
| analytics | STRING | β |