Comfy-agent curated_ep47_acestep_v1_3_5b_text_to_music_instrumental

install

source · Clone the upstream repo

git clone https://github.com/steliosot/comfy-agent

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/steliosot/comfy-agent "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/workflows/audio/curated_ep47_acestep_v1_3_5b_text_to_music_instrumental" ~/.claude/skills/steliosot-comfy-agent-curated-ep47-acestep-v1-3-5b-text-to-music-instrumental-dd8cf3 && rm -rf "$T"

manifest: skills/workflows/audio/curated_ep47_acestep_v1_3_5b_text_to_music_instrumental/SKILL.md

source content

curated_ep47_acestep_v1_3_5b_text_to_music_instrumental

Curated workflow skill generated from

EP47 AceStep V1 3.5b text to music - Instrumental.json

Capability Family

```
audio
```

Inputs

Optional runtime overrides supported by

run(...)

```
prompt
```
```
negative_prompt
```
```
width
```
,
```
height
```
```
seed
```
,
```
steps
```
,
```
cfg
```
```
sampler_name
```
,
```
scheduler
```
,
```
denoise
```
```
server
```
,
```
headers
```
,
```
api_prefix
```

Outputs

Returns JSON with:
- ```
status
```
- ```
prompt_id
```
- ```
output_images
```
  (includes image/video entries reported by Comfy history)

Model Requirements

checkpoint

ace_step_v1_3.5b.safetensors

models/checkpoints

Custom Node Requirements

None detected.

Links Extracted From Workflow Notes

Source

Original:

comfy-data/workflows/EP47 AceStep V1 3.5b text to music - Instrumental.json

Routing Metadata

Family:
```
audio
```
Input modalities:
```
text_prompt
```
Output modalities:
```
audio/wav
```
Model families:
```
sd3
```
Node count:
```
10
```
Complexity score:
```
4
```
Resource profile:
```
medium
```

Estimated runtime:

moderate (about 30-120s depending on server)

Max latent resolution hint:
```
None
```
x
```
None
```
Max sampler steps hint:
```
50
```

Detected Models

checkpoint

ace_step_v1_3.5b.safetensors

models/checkpoints

Detected Custom Nodes

None detected.

Runtime Warnings

Audio generation may take longer on CPU-only or low-VRAM servers.
Moderate-high sampler steps detected (>=40); runtime may be longer.