JettHu/ComfyUI-TCD

ComfyUI TCD implementation

47
/ 100
Emerging

Implements a distillation-based sampler that achieves superior image quality compared to LCM in fewer denoising steps by leveraging the TCD (Trajectory Consistency Distillation) technique, which compresses knowledge from pre-trained diffusion models. The custom node provides configurable stochasticity control via eta parameter to adjust detail richness, supports variable step counts with maintained quality scaling, and integrates scheduler options (`simple`, `sgm_uniform`) alongside standard ComfyUI sampling parameters.

140 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

140

Forks

11

Language

Python

License

Apache-2.0

Last pushed

Jan 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JettHu/ComfyUI-TCD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.