THUDM / FastLDM
Inference speed-up for stable-diffusion (ldm) with TensorRT.
☆35Updated last year
Related projects ⓘ
Alternatives and complementary repositories for FastLDM
- stable diffusion, controlnet, tensorrt, accelerate☆53Updated last year
- Quantized stable-diffusion cutting down memory 75%, testing in streamlit, deploying in container☆54Updated this week
- ☆66Updated last year
- NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that del…☆25Updated last year
- A more efficient GLM implementation!☆55Updated last year
- A fine tune version of Stable Diffusion model on self-translate 10k diffusiondb Chinese Corpus and "extend" it☆31Updated last year
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆41Updated 2 months ago
- ☆24Updated last year
- DreamDance: Personalized Text-to-video Generation by Combining Text-to-Image Synthesis and Motion Transfer☆14Updated last year
- CLIP中文encoder☆21Updated 2 years ago
- ☆21Updated 11 months ago
- ☆30Updated 6 months ago
- Models and examples built with OneFlow☆96Updated last month
- Chinese CLIP models with SOTA performance.☆48Updated last year
- Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning☆28Updated last year
- official code for paper: Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark☆31Updated 10 months ago
- minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora☆38Updated 7 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆15Updated 5 months ago
- ☆34Updated last year
- ☆82Updated 11 months ago
- Chinese Stable Diffusion, zh SD,中文文生图，中文SD，中文Stable Diffusion☆44Updated 8 months ago
- ☆21Updated 5 months ago
- Kanchil（鼷鹿）是世界上最小的偶蹄目动物，这个开源项目意在探索小模型（6B以下）是否也能具备和人类偏好对齐的能力。☆114Updated last year
- Stable-diffusion-WebUI extensions, which enable tensorrt accelerated Unet for SDXL base model☆12Updated last year
- MODNet for clothing matting☆16Updated 3 years ago
- OpenLLaMA-Chinese, a permissively licensed open source instruction-following models based on OpenLLaMA☆64Updated last year
- A example pipeline to use InstructPix2Pix and the associated fine-tuned motion module☆31Updated last year
- ☆21Updated 3 months ago
- Empirical Study Towards Building An Effective Multi-Modal Large Language Model☆23Updated last year