comfyui-research

Files (3)

• SKILL.md
• watch-list.yaml · references/
• last-research-run.json · state/

SKILL.md (first lines)

# ComfyUI Research Skill

> All recommendations in this skill are subordinate to `state/inventory.json`, `foundation/hardware-profile.md`, and current version constraints.

Keeps the VideoAgent knowledge base current by monitoring sources, extracting knowledge, and flagging stale information.

## Triggers

- **On demand**: The user asks to research or check for updates.
- **Stale dependency**: The active task depends on a claim flagged by `references/staleness-report.md`.
- **Session start**: Read the staleness report only; do not launch external research automatically.

## Research Pipeline

### 1. Discovery

Search for new developments only after research has been triggered. Prefer official
release notes, repositories, and model cards; use community material as secondary
technique evidence.

**YouTube Channels (technique extraction):**
| Channel | Focus | URL |
|---------|-------|-----|
| Pixaroma | ComfyUI tutorials, GGUF, beginner-friendly | youtube.com/@pixaroma |
| Kijai | Advanced nodes, model implementations | youtube.com/@Kijai |
| Sebastian Kamph | ComfyUI workflows, automation | youtube.com/@sebastiankamph |
| Olivio Sarikas | AI art techniques, ComfyUI | youtube.com/@OlivioSarikas |
| Matt Wolfe | AI tool roundups | youtube.com/@maboroshi |
| Nerdy Rodent | Stable Diffusion deep dives | youtube.com/@NerdyRodent |

**GitHub Repositories (node/model updates):**
| Repository | What to Check |
|-----------|---------------|
| comfyanonymous/ComfyUI | Releases, breaking changes |
| Kosinkadink/ComfyUI-AnimateDiff-Evolved | New motion modules |
| cubiq/ComfyUI_IPAdapter_plus | Maintenance status, forks |
| ltdrdata/ComfyUI-Impact-Pack | FaceDetailer updates |
| Official Wan repositories linked by the Wan-AI publisher | Releases and implementation changes |
| hzwer/Practical-RIFE | Interpolation updates |
| resemble-ai/chatterbox | Voice model updates |
| SWivid/F5-TTS | TTS updates |

**HuggingFace (model releases):**
- Trending models: `huggingface.co/models?sort=trending`
- Filter: diffusers, video, audio, text-to-image
- Watch for: New FLUX variants, Wan updates, identity models, voice models

### 2. Extraction

For each discovery, extract structured knowledge:

**From YouTube videos:**
If available, use a transcript-analysis skill to:
1. Get transcript
2. Identify new models mentioned (name, source, requirements)
3. Identify new techniques (workflow changes, parameter discoveries)
4. Identify new nodes (package name, what it does)
5. Note any benchmark results or comparisons

**From GitHub releases:**
1. Check release notes for breaking changes
2. Identify new features or supported models
3. Note version requirements
4. Check if deprecated features affect our workflows

**From HuggingFace:**
1. Model card: architecture, training data, requirements
2. VRAM requirements and quantization options
3. ComfyUI compatibility (is there a node?)
4. Quality comparison vs current recommendations

### 3. Integration

Update reference files with timestamped entries:

```markdown
<!-- Updated: 2026-02-06 | Source: Pixaroma Ep 45 -->
### New Model: XYZ
- Download: {url}
- VRAM: {requirement}
- Notes: {key findings}
```

**Which file to update:**
| Finding Type | Update File |
|-------------|-------------|
| New model | `references/models.md` |
| New workflow technique | `references/workflows.md` |
| LoRA training discovery | `references/lora-training.md` |
| Voice tool update | `references/voice-synthesis.md` |
| New prompt technique | `references/prompt-templates.md` |
| Bug workaround | `references/troubleshooting.md` |
| Model landscape shift | `foundation/model-landscape.md` |

### 4. Staleness Audit

Scan all reference files for `<!-- Updated: -->` timestamps:

**Thresholds:**
| Category | Max Age | Action |
|----------|---------|--------|
| Models | 3 months | Flag: "Model recommendations may be outdated" |
| Nodes | 2 months | Flag: "Custom node versions may have updates" |
| Techniques | 6 months | Flag: "Techniques may have been superseded" |
| Voice tools | 3 months | Flag: "Voice synthesis landscape may have changed" |

**Generate report**: Update `references/staleness-report.md` with current status.

## Research State

Maintained in `skills/comfyui-research/state/`:

```
state/
  last-research-run.json    # When, what was checked, what was found
  watch-list.yaml           # Sources to monitor (see references/)
```

### last-research-run.json

From calebmills99/VUORSE-VORTEX, MIT.

More from calebmills99/VUORSE-VORTEX