What models can run on Livepeer, and which are better suited?This page lists all known model families commonly used via ComfyUI, with compatibility ratings for Livepeer’s real-time, GPU-worker constraints. Nothing here implies that a listed model is officially supported or pre-loaded on the network - it reflects whether a model’s execution shape fits Livepeer well.
Legend
- ✓ Likely runnable - fits real-time / GPU-worker constraints
- ⚠ Conditional - depends on latency, VRAM, orchestration, or batching
- ✗ Not suitable - design mismatch: stateful, CPU-bound, or non-deterministic
1. Diffusion Models (Image / Video)
Stable Diffusion family
| Model | Fit | Notes |
|---|
Video diffusion models
| Model | Fit | Notes |
|---|
2. Control & Conditioning Models
ControlNet
| Model | Fit | Notes |
|---|
T2I / I2I Adapters
| Model | Fit | Notes |
|---|
3. Encoders, VAEs, and Latents
| Model | Fit | Notes |
|---|
4. Vision Models (Non-Diffusion)
Detection / Segmentation
| Model | Fit | Notes |
|---|
Depth / Geometry
| Model | Fit | Notes |
|---|
5. Face, Pose & Human Models
| Model | Fit | Notes |
|---|
6. Audio & Music Models
| Model | Fit | Notes |
|---|
For real-time audio workloads (live ASR, live translation, streaming transcription), see Workload Fit → ASR pipeline examples. These use Whisper or similar and are excellent fits.
7. Multimodal & VLMs
| Model | Fit | Notes |
|---|
8. LLMs (Text-Centric)
| Model | Fit | Notes |
|---|
9. 3D / NeRF / World Models
| Model | Fit | Notes |
|---|
10. Utility / Pre/Post Models
| Model | Fit | Notes |
|---|
Core takeaway
ComfyUI can orchestrate almost any PyTorch model. But:- Livepeer favours stateless, frame-based, deterministic inference
- Long-running, stateful, or batch-only models are fundamentally incompatible
- Real-time video imposes hard physics limits, not software ones