--- license: creativeml-openrail-m language: - en tags: - art - Stable Diffusion --- ## Model Card for lyraSD We consider the Diffusers as the much more extendable framework for the SD ecosystem. Therefore, we have made a **pivot to Diffusers**, leading to a complete update of lyraSD. lyraSD is currently the **fastest Stable Diffusion model** that can 100% align the outputs of **Diffusers** available, boasting an inference cost of only **0.36 seconds** for a 512x512 image, accelerating the process up to **50% faster** than the original version. Among its main features are: - **All Commonly used** SD1.5 and SDXL pipelines - - Text2Img - - Img2Img - - Inpainting - - ControlNetText2Img - - ControlNetImg2Img - - IpAdapterText2Img - **Fast ControlNet Hot Swap**: Can hot swap a ControlNet model weights within 0.6s - **Fast LoRA Hot Swap**: Can hot swap a Lora within 0.14s - 100% likeness to diffusers output - Supported Devices: Any GPU with SM version >= 80. For example, Nvidia Nvidia Ampere architecture (A2, A10, A16, A30, A40, A100), RTX 4090, 3080 and etc. ## Speed ### test environment - Device: Nvidia A100 40G - Nvidia driver version: 525.105.17 - Nvidia cuda version: 12.0 - Percision:fp16 - Steps: 20 - Sampler: EulerA ### SD1.5 Text2Img Performance ![Alt text](images/sd_txt2img.png) ### SD1.5 ControlNet-Text2Img Performance ![Alt text](images/sd_controlnet_txt2img.png) ### SDXL Text2Img Performance ![Alt text](images/sdxl_txt2img.png) ### SDXL ControlNet-Text2Img Performance ![Alt text](images/sdxl_controlnet_txt2img.png) ### SD Model Load Performance ![Alt text](images/model_load_performance.png) ## Model Sources SD1.5 - **Checkpoint:** https://civitai.com/models/7371/rev-animated - **ControlNet:** https://huggingface.co/lllyasviel/sd-controlnet-canny - **Lora:** https://civitai.com/models/18323?modelVersionId=46846 SDXL - **Checkpoint:** https://civitai.com/models/43977?modelVersionId=227916 - **ControlNet:** https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0 - **Lora:** https://civitai.com/models/245889/dissolve-style-lora-15sdxl ## SD1.5 Text2Img Uses ```python import torch import time from lyrasd_model import LyraSdTxt2ImgPipeline # 存放模型文件的路径，应该包含一下结构(和diffusers一致)： # 1. clip 模型 # 2. 转换好的优化后的 unet 模型，放入其中的 unet_bins 文件夹 # 3. vae 模型 # 4. scheduler 配置 # LyraSD 的 C++ 编译动态链接库，其中包含 C++ CUDA 计算的细节 lib_path = "./lyrasd_model/lyrasd_lib/libth_lyrasd_cu12_sm80.so" model_path = "./models/rev-animated" lora_path = "./models/xiaorenshu.safetensors" torch.classes.load_library(lib_path) # 构建 Txt2Img 的 Pipeline model = LyraSdTxt2ImgPipeline() model.reload_pipe(model_path) # load lora # lora model path, name，lora strength model.load_lora_v2(lora_path, "xiaorenshu", 0.4) # 准备应用的输入和超参数 prompt = "a cat, cute, cartoon, concise, traditional, chinese painting, Tang and Song Dynasties, masterpiece, 4k, 8k, UHD, best quality" negative_prompt = "(((horrible))), (((scary))), (((naked))), (((large breasts))), high saturation, colorful, human:2, body:2, low quality, bad quality, lowres, out of frame, duplicate, watermark, signature, text, frames, cut, cropped, malformed limbs, extra limbs, (((missing arms))), (((missing legs)))" height, width = 512, 512 steps = 20 guidance_scale = 7 generator = torch.Generator().manual_seed(123) num_images = 1 start = time.perf_counter() # 推理生成 images = model(prompt, height, width, steps, guidance_scale, negative_prompt, num_images, generator=generator) print("image gen cost: ",time.perf_counter() - start) # 存储生成的图片 for i, image in enumerate(images): image.save(f"outputs/res_txt2img_lora_{i}.png") # unload lora， lora’s name, clear lora cache model.unload_lora_v2("xiaorenshu", True) ``` ## SDXL Text2Img Uses ```python import torch import time from lyrasd_model import LyraSdXLTxt2ImgPipeline # 存放模型文件的路径，应该包含一下结构： # 1. clip 模型 # 2. 转换好的优化后的 unet 模型，放入其中的 unet_bins 文件夹 # 3. vae 模型 # 4. scheduler 配置 # LyraSD 的 C++ 编译动态链接库，其中包含 C++ CUDA 计算的细节 lib_path = "./lyrasd_model/lyrasd_lib/libth_lyrasd_cu12_sm80.so" model_path = "./models/helloworldSDXL20Fp16" lora_path = "./models/dissolve_sdxl.safetensors" torch.classes.load_library(lib_path) # 构建 Txt2Img 的 Pipeline model = LyraSdXLTxt2ImgPipeline() model.reload_pipe(model_path) # load lora # lora model path, name，lora strength model.load_lora_v2(lora_path, "dissolve_sdxl", 0.4) # 准备应用的输入和超参数 prompt = "a cat, cute, cartoon, concise, traditional, chinese painting, Tang and Song Dynasties, masterpiece, 4k, 8k, UHD, best quality" negative_prompt = "(((horrible))), (((scary))), (((naked))), (((large breasts))), high saturation, colorful, human:2, body:2, low quality, bad quality, lowres, out of frame, duplicate, watermark, signature, text, frames, cut, cropped, malformed limbs, extra limbs, (((missing arms))), (((missing legs)))" height, width = 512, 512 steps = 20 guidance_scale = 7 generator = torch.Generator().manual_seed(123) num_images = 1 start = time.perf_counter() # 推理生成 images = model( prompt, height=height, width=width, num_inference_steps=steps, num_images_per_prompt=1, guidance_scale=guidance_scale, negative_prompt=negative_prompt, generator=generator ) print("image gen cost: ",time.perf_counter() - start) # 存储生成的图片 for i, image in enumerate(images): image.save(f"outputs/res_txt2img_xl_lora_{i}.png") # unload lora，参数为 lora 的名字，是否清除 lora 缓存 model.unload_lora_v2("dissolve_sdxl", True) ``` ## Demo output ### Text2Img #### SD1.5 Text2Img ![text2img_demo](./outputs/res_txt2img_0.png) #### SD1.5 Text2Img with Lora ![text2img_demo](./outputs/res_txt2img_lora_0.png) #### SDXL Text2Img ![text2img_demo](./outputs/res_sdxl_txt2img_0.png) #### SDXL Text2Img with Lora ![text2img_demo](./outputs/res_txt2img_xl_lora_0.png) ### ControlNet Text2Img #### Control Image ![text2img_demo](./control_bird_canny.png) #### SD1.5 ControlNet Text2Img Output ![text2img_demo](./outputs/res_controlnet_txt2img_0.png) #### SDXL ControlNet Text2Img Output ![text2img_demo](./outputs/res_controlnet_sdxl_txt2img_0.png) ## Docker Environment Recommendation - For Cuda 12.X: we recommend ```yibolu96/lyrasd_workspace:1.0.0``` ```bash docker pull yibolu96/lyrasd_workspace:1.0.0 docker run --rm -it --gpus all -v ./:/lyraSD yibolu96/lyrasd_workspace:1.0.0 pip install -r requirements.txt python txt2img_demo.py ``` ## Citation ``` bibtex @Misc{lyraSD_2024, author = {Kangjian Wu, Zhengtao Wang, Yibo Lu, Haoxiong Su, Sa Xiao, Bin Wu}, title = {lyraSD: Accelerating Stable Diffusion with best flexibility}, howpublished = {\url{https://huggingface.co/TMElyralab/lyraSD}}, year = {2024} } ``` ## Report bug - start a discussion to report any bugs!--> https://huggingface.co/TMElyralab/lyraSD/discussions - report bug with a `[bug]` mark in the title.