The Workflow was setup to have a clean "GUI" showing only parameters that matter, so you might want to toggle off Link visibility, like in above screenshot.
V1.8 Ace Step 1.5. Turbo and SFT normal and XL model with Ollama. Text to Audio/Song (examples below).
small update on Lora handling to better include Lora trigger words/phrases
Check this link with 1.5.Turbo XL Loras by Ryanontheinside: https://huggingface.co/ryanontheinside/models
1.5 XL Loras can be loaded on any XL Slot (Turbo, SFT or merges), it improve the sound very well, like more authentic guitars for rock&metal, etc. Also song structures follow the genre better.
Loras require a trigger word that can be found on the main page per Lora of above link. Use the trigger word in the new node "Pretext" within the Input section of the workflow, added around 25 of those triggers to a Note in the WF for copy&paste.
See post in discussion below for more info.
Key features:
Can use any Song, Artist as reference or any other description to generate tags and lyrics.
Will output up to 4 songs, each by Turbo, SFT, Turbo XL and SFT XL model (or any merge or Base model).
Keyscales, bpm and song duration can be randomized.
able to use dynamic prompts.
creates suitable songtitle and filenames with Ollama.
saves songs as MP3 with tags like lyrics, artist, genre, etc.
V1.7 Ace Step 1.5. Turbo and SFT normal and XL model with Ollama. Text to Audio/Song.
replaced the "save Mp3" nodes to allow ID3 tags to include data like artist name, bpm, genre, lyrics, etc.
requires custom node: https://github.com/mattjohnpowell/comfyui-audio-expo
added a feature to save all relevant data (tags, lyrics, etc.) as a separate text (.txt) file
audio render processing remains unchanged to previous version
V1.6 Ace Step 1.5. Turbo and SFT normal and XL model with Ollama.
updated the settings for XL models and added a 3rd System Prompt for tags to chose, with more descriptive song descriptions.
1.5 XL SFT pipeline now has an "Adaptive Projected Guidance" node and negative prompt.
** See below some tips which model and settings to start with.
V1.5 Ace Step 1.5. Turbo and SFT normal and XL model with Ollama:
setup to create up to 4 tracks in a run, 2x Ace1.5 and 2x Ace1.5 XL, each with Turbo and SFT model, to compare (can be individually switched on/off)
VAE changed to tiled Audio VAE decode, uses less Vram.
V1.2 Ace Step 1.5. Turbo and SFT model with Ollama Text to Audio/Song
small update to GUI, system prompts and SFT sampler "engine"
V1.0 Ace Step 1.5. Turbo and SFT model with Ollama Text to Audio/Song
Ace Step uses TAGS and LYRICS to create a song. These can be generated by Ollama or by own prompts.
Download Files:
Ace Step 1.5 TURBO model: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/diffusion_models
Ace Step 1.5 SFT model: https://huggingface.co/ACE-Step/acestep-v15-sft/tree/main (download model.safetensor and rename it)
Ace Step 1.5 XL Models: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/diffusion_models
Ace Step 1.5 XL Model merges (i.e. merge of turbo with SFT): https://huggingface.co/Aryanne/acestep-v15-test-merges/tree/main/xl
Textencoder: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/text_encoders (Qwen_0.6b and Qwen_4b required, 1.7b is a smaller alternative to 4b)
VAE: https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/tree/main/split_files/vae
alternative VAE: https://huggingface.co/megagrump/Ace-Step-1.5-ScragVAE-ComfyUI
Ollama Models, required for tags, lyrics and songtitle, you can choose 1,2 or 3 different models, tags and lyrics might need a bigger model >7b, songtitle can use a smaller model:
https://ollama.com/mirage335/Llama-3-NeuralDaredevil-8B-abliterated-virtuoso (allround model, fast, usable for tags, lyrics and songtitle, recommended)
https://ollama.com/huihui_ai/qwen3-vl-abliterated (for tags and lyrics, able to use thinking)
https://ollama.com/artifish/llama3.2-uncensored (small and fast for songtitle and tags)
Alternative Turbo Models and merges (normal, non XL) :
Turbo continuous: https://huggingface.co/ACE-Step/acestep-v15-turbo-continuous/tree/main
Turbo-Shift1: https://huggingface.co/ACE-Step/acestep-v15-turbo-shift1/tree/main
Turbo-Shift3: https://huggingface.co/ACE-Step/acestep-v15-turbo-shift3/tree/main
Merges of SFT, Turbo and Base model: https://huggingface.co/Aryanne/acestep-v15-test-merges/tree/main
GGUF Models "normal" and XL: https://huggingface.co/Serveurperso/ACE-Step-1.5-GGUF/tree/main
Which models to start with ?
If you just want to try it first before downloading all those models, start with 1 model only, recommend the Turbo or Turbo XL model.
My current choice for normal model: Turbo-SFT merge_ta_0.5 & Turbo-Shift1, using these settings:
Turbo-SFT_merge model with sampler: er_sde, scheduler: beta57 (or beta), 22 steps
Turbo-Shift1 model with sampler euler, scheduler: normal, 138 steps
XL Model settings:
XL Turbo-SFT merge model: sampler: er_sde, scheduler: sgm_uniform, 40 steps
alternative: sampler: res_s2, scheduler beta57 (requires RES4LYF custom nodes)
XL SFT model: sampler: euler (or res_2s), scheduler: normal, 46 steps, CFG = 7.3, Adaptive Projected Guidance: eta = 1.05, norm_thresh= 1.3, momentum=0.0. Increase norm_thresh as the main parameter. These settings deliver "stabil" output for XL SFT,Base and their merges. The merges sound way better, pure SFT or Base introduce a lot of noise. I bypassed ModelSamplingAuraflow (see node next to model loader node). I think the base-turbo XL model merge fits well in that slot.
Disable "generate_audio_codes" in "TextEncodeAceStep" node to get different results, it works very well for many genres and reduces process time.
Ollama Model: Llama-3-NeuralDaredevil-8b-abliterated
More infos on models see thread below in discussion.
Save Location:
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 diffusion_models/
│ │ └── acestep_v1.5_turbo.safetensors
│ ├── 📂 text_encoders/
│ │ ├── qwen_0.6b_ace15.safetensors
│ │ └── qwen_4b_ace15.safetensors (or 1.7b)
│ └── 📂 vae/
│ └── ace_1.5_vae.safetensors
Custom Nodes used:
https://github.com/mattjohnpowell/comfyui-audio-expo (as of V1.7)
optional (use Beta57 scheduler for a bit more punch, requires RES4LYF): https://github.com/ClownsharkBatwing/RES4LYF
Examples various styles:
With Lora:
https://soundcloud.com/tele-joe/city-of-silent-sirens_gothic
https://soundcloud.com/tele-joe/forgotten-blazes_future-bass
No Lora:
https://soundcloud.com/tele-joe/burning-echoes-of-the-fallen
https://soundcloud.com/tele-joe/firestorms_unleashed_turbo_000
https://soundcloud.com/tele-joe/westsidevibesforever_funkhipho
Ollama help:
Install Ollama from https://ollama.com/
download a model: Go to a model page, chose a model , then hit the copy button, i.e. https://ollama.com/mirage335/Llama-3-NeuralDaredevil-8B-abliterated-virtuoso
open terminal and paste the model name, i.e.: ollama run huihui_ai/qwen3-vl-abliterated
model will be downloaded and can be selected in green comfy node "Ollama Connectivity". Hit "Reconnect" to refresh.
Description
Workflow setup to run AceStep 1.5 and 1.5 XL Models
with updated Settings for XL models
FAQ
Comments (13)
I love everything about this workflow, except for the upscaler.
Hey, thanks for the buzz. Glad it works for you.
What do you mean by upscaler? I did not include any, not that I know...
When i try to install the missing custom nodes trough the comfyui manager OllamaConnectivityV2, OllamaGenerateV2, OllamaOptionsV2 it says the nodes may have been removed from ComfyRegistry does someone else have the same problems?
Strange, I am not aware about OllamaV2. Maybe try to install the repo manually into your custom-nodes folder: https://github.com/stavsap/comfyui-ollama
This one is pretty good. The only is that I wish it had a node for saving the lyrics. I tried to make a node for it but it doesn't save it as a text file. If it saved the lyrics and other info about each song like the seed and bpm etc this would be even better even if was in a separate workflow. Thanks!
great idea, I would like to save all the relevant data , bpm, lyrics, genre etc. with in the metadata of the generated mp3. Probably doable only with additional custom nodes, which I like to avoid. Anyway will check how to save the lyrics as text.
so there is this node "Save Text" from easy-use custom nodes pack, which is already part of the workflow, it can save lyrics as text file, you can hook it up to the lyrics text node and even capture the songname output node and connect it as filename.
to include bpm, seed etc. you can use concatenate node, there are some of those in the ollama group. So you combine those data by concatenating it to a big string, then let is save as text file.
@tremolo28Â Thanks for the reply. I use that node the problem is that I don't know how to get it to save the lyrics as a .txt or give it any extension. If you could tell me how that would help and save you having to included it and refer others to that information.
@tvhead1980Â the setup to save text file works like this:
1. add node "Save Text" from easy-use custom nodes.
2. connect the output of the "applied lyrics" node to the text input of above node
3. set "output_file_path" to a folder you like to save the textfile
4. set "file_extension" to txt
5. connect the Songtitle output to the "file_name" input of the save text node / or just set a filename.
@tremolo28Â There is no where to do step 4 to set "file_extension" to txt
@tvhead1980Â Strange, I have "file_extension" in my save text node, I can select between .txt or .csv. I am using latest easy-use nodes with version 1.36: https://github.com/yolain/ComfyUI-Easy-Use
@tvhead1980Â worked on the workflow to integrate both, saving lyrics as text file and within the mp3 tags. Need to do some clean-up and wait until civitAi runs stable again, might put it up beg of next week.
@tremolo28Â Sounds good, thanks.