Target-Driven-Distillation
Consistency Distillation with Target Timestep Selection and Decoupled Guidance
Fine-Tuning PlatformMLOps & Experiment TrackingOpen Source
About
Target-Driven Distillation (TDD) is a state-of-the-art consistency distillation model that largely accelerates the inference processes of diffusion models. Using its delicate strategies of target timestep selection and decoupled guidance, models distilled by TDD can generated highly detailed images with only a few steps.
Open Source Health
- Stars
- 112
- Forks
- 14
- License
- Not stated
- Last commit
- 2 years ago
Python
Alternatives to Target-Driven-Distillation
Peftby Hugging Face🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Sophia Script For Windowsby Dmitry Nefedovzap: The most powerful PowerShell module for fine-tuning Windows 10 & Windows 11 on GitHub
KTransformersby kvcache.aiA Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
LongWriterby THUKEG[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
Regress Lmby Google DeepMindLibrary for sequence-to-sequence numeric prediction, applicable to any tokenizable input, and allows pretraining and fine-tuning over multiple tasks.
Resources & Links
Related Categories
Using Target-Driven-Distillation?
Track its cost next to the rest of your stack and get a reminder before it renews.
Add to my stackVendor
FireRedTeam
小红书Super Intelligence部门下属基础算法实验室， Xiaohongshu Super Intelligence fundamental technology lab
