--- tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - diffusers-training - text-to-image - diffusers - lora - template:sd-lora widget: - text: 'a LEO cat on the floor' output: url: "image_0.png" - text: 'a LEO cat on the floor' output: url: "image_1.png" - text: 'a LEO cat on the floor' output: url: "image_2.png" - text: 'a LEO cat on the floor' output: url: "image_3.png" base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: photo of a LEO cat license: openrail++ --- # SDXL LoRA DreamBooth - greerben0/leo-cat-sdxl-lora-v2 ## Model description ### These are greerben0/leo-cat-sdxl-lora-v2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. ## Download model ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke - **LoRA**: download **[`leo-cat-sdxl-lora-v2.safetensors` here ๐Ÿ’พ](/greerben0/leo-cat-sdxl-lora-v2/blob/main/leo-cat-sdxl-lora-v2.safetensors)**. - Place it on your `models/Lora` folder. - On AUTOMATIC1111, load the LoRA by adding `` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/). - *Embeddings*: download **[`leo-cat-sdxl-lora-v2_emb.safetensors` here ๐Ÿ’พ](/greerben0/leo-cat-sdxl-lora-v2/blob/main/leo-cat-sdxl-lora-v2_emb.safetensors)**. - Place it on it on your `embeddings` folder - Use it by adding `leo-cat-sdxl-lora-v2_emb` to your prompt. For example, `photo of a LEO cat` (you need both the LoRA and the embeddings as they were trained together for this LoRA) ## Use it with the [๐Ÿงจ diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch from huggingface_hub import hf_hub_download from safetensors.torch import load_file pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('greerben0/leo-cat-sdxl-lora-v2', weight_name='pytorch_lora_weights.safetensors') embedding_path = hf_hub_download(repo_id='greerben0/leo-cat-sdxl-lora-v2', filename='leo-cat-sdxl-lora-v2_emb.safetensors', repo_type="model") state_dict = load_file(embedding_path) pipeline.load_textual_inversion(state_dict["clip_l"], token=[], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer) pipeline.load_textual_inversion(state_dict["clip_g"], token=[], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2) image = pipeline('a LEO cat on the floor').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Trigger words To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens: to trigger concept `TOK` โ†’ use `` in your prompt ## Details All [Files & versions](/greerben0/leo-cat-sdxl-lora-v2/tree/main). The weights were trained using [๐Ÿงจ diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py). LoRA for the text encoder was enabled. False. Pivotal tuning was enabled: True. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.