--- tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - lora - template:sd-lora widget: - text: a beautiful painting of a tired young mother like an indian goddess, flying away to heaven with children on her shoulder, laptop in her lap, in the style of Raja Ravi Varma output: url: image-0.png - text: a beautiful painting of a tired young mother like an indian goddess, flying away to heaven with children on her shoulder, laptop in her hands, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-1.png - text: a beautiful painting of a young indian mother with many arms like an indian goddess sitting on a rock with a child on her arms, and a laptop in her arms, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-2.png - text: a beautiful painting of a young indian mother with many arms like an indian goddess sitting on a rock with a child on her arms, and a laptop in her arms, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-3.png - text: a beautiful painting of a young indian mother with many arms like an indian goddess sitting on a rock with a child on her arms, and a laptop in her arms, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-4.png - text: a beautiful painting of a young indian mother with many arms like an indian goddess sitting on a rock with a child on her arms, and a laptop in her arms, in the style of Raja Ravi Varma output: url: image-5.png - text: a beautiful painting of a young indian mother with many arms like an indian goddess sitting on a cloud with a child on her arms, and a laptop in her arms, in the style of Raja Ravi Varma output: url: image-6.png - text: a beautiful painting of a young indian mother with an indian goddess flying in the air with a child on her arms, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-7.png - text: a beautiful painting of a young indian mother with an indian goddess flying in the air with a child on her arms, in the style of Raja Ravi Varma output: url: image-8.png - text: a beautiful painting of a young indian mother with an indian goddess flying in the air with a child on her arms, in the style of Raja Ravi Varma output: url: image-9.png - text: a beautiful painting of a young indian mother with many arms like an indian goddess sitting on a rock with a child on her arms, and a laptop in her arms, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-10.png - text: a beautiful painting of a young indian mother with many arms like an indian goddess sitting on a rock with a child on her arms, and a laptop in her arms, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-11.png - text: a beautiful painting of a tired young mother like an indian goddess, flying away to heaven with children on her shoulder, laptop in her lap, in the style of Raja Ravi Varma output: url: image-12.png - text: a beautiful painting of a tired young mother in a corporate suit like an indian goddess, flying away to heaven, laptop in her lap, there are cherubs in the background, in the style of Raja Ravi Varma output: url: image-13.png - text: a beautiful painting of a tired young mother like an indian goddess, flying away to heaven with children on her shoulder, laptop in her lap, in the style of Raja Ravi Varma output: url: image-14.png base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: license: openrail++ --- # SDXL LoRA DreamBooth - computational-mama/corporateshwari ## Model description ### These are computational-mama/corporateshwari 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 **[`corporateshwari.safetensors` here ๐Ÿ’พ](/computational-mama/corporateshwari/blob/main/corporateshwari.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 **[`corporateshwari_emb.safetensors` here ๐Ÿ’พ](/computational-mama/corporateshwari/blob/main/corporateshwari_emb.safetensors)**. - Place it on it on your `embeddings` folder - Use it by adding `corporateshwari_emb` to your prompt. (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('computational-mama/corporateshwari', weight_name='pytorch_lora_weights.safetensors') embedding_path = hf_hub_download(repo_id='computational-mama/corporateshwari', filename='corporateshwari_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('').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](/computational-mama/corporateshwari/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.