LCM-LoRA SDXL
An SDXL LoRA adapter that enables Latent Consistency Model inference in roughly two to eight denoising steps.
Fuente del modelo
- Tipo
- LoRA
- Tamaño del archivo
- 376 MB
- Modelo base
- stabilityai/stable-diffusion-xl-base-1.0
- Versión
- vpytorch_lora_weights
- Actualizado
- 21 oct 2026
- Publicador
- @latent-consistency
- Descargas
- 42,9 mil
- Parámetros
- 6M
- Fuente
- Hugging Face
Resumen
LCM-LoRA SDXL is a distilled consistency adapter for Stable Diffusion XL. It attaches to an SDXL base model and uses an LCM scheduler to reduce generation to roughly two to eight denoising steps. The adapter supports text-to-image and inpainting workflows and can be combined with compatible style LoRAs; the official repository includes weights and usage examples.
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 21 oct
Artefactos del modelo
1 artefacto
Artefactos del modelo
1 artefactopytorch_lora_weights.safetensors
safetensors · 376 MB · SHA-256 a764e6859b6e…9141 · Hugging Face
DescargarExtractos de fuentes
3 extractos
Extractos de fuentes
3 extractos--- library_name: diffusers base_model: stabilityai/stable-diffusion-xl-base-1.0 tags: - lora - text-to-image license: openrail++ inference: false --- # Latent Consistency Model (LCM) LoRA: SDXL Latent Consistency Model (LCM) LoRA was proposed in [LCM-LoRA: A universal Stable-Diffusion Acceleration Module](https://arxiv.org/abs/2311.05556) by *Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu et al.* It is a distilled consistency adapter for [`stable-diffusion-xl-base-1.0`](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) that allows to reduce the number of inference steps to only between **2 - 8 steps**. | Model | Params / M | |----------------------------------------------------------------------------|------------| | [lcm-lora-sdv1-5](https://huggingface.co/latent-consistency/lcm-lora-sdv1-5) | 67.5 | | [lcm-lora-ssd-1b](https://huggingface.co/latent-consistency/lcm-lora-ssd-1b) | 105 | | [**lcm-lora-sdxl**](https://huggingface.co/latent-consistency/lcm-lora-sdxl) | **197M** | ## Usage LCM-LoRA is supported in 🤗 Hugging Face Diffusers library from version v0.23.0 onwards. To run the model, first install the latest version of the Diffusers library as well as `peft`, `accelerate` and `transformers`. audio dataset from the Hugging Face Hub: ```bash pip install --upgrade pip pip install --upgrade diffusers transformers accelerate peft ``` ***Note: For detailed usage examples we recommend you to check out our official [LCM-LoRA docs](https://huggingface.co/docs/diffusers/main/en/using-diffusers/inference_with_lcm_lora)*** ### Text-to-Image The adapter can be loaded with it's base model `stabilityai/stable-diffusion-xl-base-1.0`. Next, the scheduler needs to be changed to [`LCMScheduler`](https://huggingface.co/docs/diffusers/v0.22.3/en/api/schedulers/lcm#diffusers.LCMScheduler) and we can reduce the number of inference steps to just 2 to 8 steps. Please make sure to either disable `guidance_scale` or use values between 1.0 and 2.0. ```python import torch from diffusers import LCMScheduler, AutoPipelineForText2Image model_id = "stabilityai/stable-diffusion-xl-base-1.0" adapter_id = "latent-consistency/lcm-lora-sdxl" pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.float16, variant="fp16") pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config) pipe.to("cuda") # load and fuse lcm lora pipe.load_l...
Source context: 42879 downloads · 775 likes · Pipeline text-to-image · Library diffusers · Repo latent-consistency/lcm-lora-sdxl
Source context: 34087 downloads · 771 likes · Pipeline text-to-image · Library diffusers · Repo latent-consistency/lcm-lora-sdxl
