THUDM / FastLDM
Inference speed-up for stable-diffusion (ldm) with TensorRT.
☆35Updated last year
Alternatives and similar repositories for FastLDM
Users that are interested in FastLDM are comparing it to the libraries listed below
Sorting:
- stable diffusion, controlnet, tensorrt, accelerate☆56Updated 2 years ago
- NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that del…☆26Updated last year
- Int8 StableFusion model☆41Updated 2 years ago
- Quantized stable-diffusion cutting down memory 75%, testing in streamlit, deploying in container☆54Updated last week
- Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning☆28Updated last year
- A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.☆13Updated 2 years ago
- Stable-diffusion-WebUI extensions, which enable tensorrt accelerated Unet for SDXL base model☆12Updated last year
- A more efficient GLM implementation!☆55Updated 2 years ago
- SealAI's stable diffusion implementation☆77Updated 4 months ago
- CLIP中文encoder☆22Updated 2 years ago
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆47Updated 8 months ago
- ☆67Updated last year
- a autodl environment for native finetune stable diffusion.☆11Updated 2 years ago
- Chinese Stable Diffusion, zh SD,中文文生图,中文SD,中文Stable Diffusion☆48Updated last year
- An efficient implementation of Stable-Diffusion-XL☆47Updated last year
- ☆54Updated 2 years ago
- 天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案☆49Updated last year
- Taiyi-Diffusion-XL训练代码☆22Updated 11 months ago
- MegEngine implementation of Diffusion Models.☆18Updated 2 years ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆20Updated 3 weeks ago
- ChatSD is designed to make image generation tasks easily☆20Updated 2 years ago
- ☆91Updated last year
- minisora-DiT, a DiT reproduction based on XTuner from the open source community MiniSora☆41Updated last year
- ☆25Updated 11 months ago
- ☆79Updated last year
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Updated last year
- LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.☆38Updated 10 months ago
- Chinese CLIP models with SOTA performance.☆55Updated last year
- ☆13Updated last year
- Our 2nd-gen LMM☆33Updated 11 months ago