| | --- |
| | tags: |
| | - stable-diffusion-xl |
| | - stable-diffusion-xl-diffusers |
| | - text-to-image |
| | - diffusers |
| | - lora |
| | - template:sd-lora |
| | widget: |
| | - text: notepad plus - note pad plus in the style of <s0><s1> |
| | output: |
| | url: image-0.png |
| | - text: a black background with a white clock on it in the style of <s0><s1> |
| | output: |
| | url: image-1.png |
| | - text: anaconda - an open source data management system in the style of <s0><s1> |
| | output: |
| | url: image-2.png |
| | - text: a smiley face with two bones on a green background in the style of <s0><s1> |
| | output: |
| | url: image-3.png |
| | - text: the vivira logo with a red and gray cross in the style of <s0><s1> |
| | output: |
| | url: image-4.png |
| | - text: amazon aws logo in the style of <s0><s1> |
| | output: |
| | url: image-5.png |
| | - text: the amazon web services logo in the style of <s0><s1> |
| | output: |
| | url: image-6.png |
| | - text: azure logo with blue triangle in the style of <s0><s1> |
| | output: |
| | url: image-7.png |
| | - text: the logo for bokkeh, a company that provides a variety of services in the |
| | style of <s0><s1> |
| | output: |
| | url: image-8.png |
| | - text: the logo for bokh in the style of <s0><s1> |
| | output: |
| | url: image-9.png |
| | - text: caddy 2 - free online storage for your photos and videos in the style of <s0><s1> |
| | output: |
| | url: image-10.png |
| | - text: the logo for dask, a cryptocurrency exchange in the style of <s0><s1> |
| | output: |
| | url: image-11.png |
| | - text: docker for windows 10 in the style of <s0><s1> |
| | output: |
| | url: image-12.png |
| | - text: a green dinosaur holding a keyboard and a piece of paper in the style of <s0><s1> |
| | output: |
| | url: image-13.png |
| | - text: numba logo with a lightning bolt in the style of <s0><s1> |
| | output: |
| | url: image-14.png |
| | - text: the dvc logo on a black background in the style of <s0><s1> |
| | output: |
| | url: image-15.png |
| | - text: the logo for elk, a company that makes software for the web in the style of |
| | <s0><s1> |
| | output: |
| | url: image-16.png |
| | - text: a black background with a white clock on it in the style of <s0><s1> |
| | output: |
| | url: image-17.png |
| | - text: fast ai logo in the style of <s0><s1> |
| | output: |
| | url: image-18.png |
| | - text: fastapi - a fast api for your app in the style of <s0><s1> |
| | output: |
| | url: image-19.png |
| | - text: a black background with a white clock on it in the style of <s0><s1> |
| | output: |
| | url: image-20.png |
| | - text: google cloud logo in the style of <s0><s1> |
| | output: |
| | url: image-21.png |
| | - text: google logo with a colorful background in the style of <s0><s1> |
| | output: |
| | url: image-22.png |
| | - text: a yellow emoticion with its hands up in the style of <s0><s1> |
| | output: |
| | url: image-23.png |
| | - text: a logo with a colorful cube in the middle in the style of <s0><s1> |
| | output: |
| | url: image-24.png |
| | - text: the jinja logo with a colorful light bulb in the style of <s0><s1> |
| | output: |
| | url: image-25.png |
| | - text: the logo for qinna, a company that provides a variety of services in the style |
| | of <s0><s1> |
| | output: |
| | url: image-26.png |
| | - text: the logo for jupyter is shown in orange and black in the style of <s0><s1> |
| | output: |
| | url: image-27.png |
| | - text: the logo for the company is a red, green and blue triangle in the style of |
| | <s0><s1> |
| | output: |
| | url: image-28.png |
| | - text: the kubernetes logo with a blue and white star in the style of <s0><s1> |
| | output: |
| | url: image-29.png |
| | - text: kubernetes is a container orchestration platform in the style of <s0><s1> |
| | output: |
| | url: image-30.png |
| | - text: milius - a free and open source video player in the style of <s0><s1> |
| | output: |
| | url: image-31.png |
| | - text: the miluus logo with a blue circle in the style of <s0><s1> |
| | output: |
| | url: image-32.png |
| | - text: the node - red logo on a red background in the style of <s0><s1> |
| | output: |
| | url: image-33.png |
| | - text: the node logo on a black background in the style of <s0><s1> |
| | output: |
| | url: image-34.png |
| | - text: the npm logo on a red background in the style of <s0><s1> |
| | output: |
| | url: image-35.png |
| | - text: numba logo on black background in the style of <s0><s1> |
| | output: |
| | url: image-36.png |
| | - text: the n logo with a blue cube in the style of <s0><s1> |
| | output: |
| | url: image-37.png |
| | - text: nvidia geforce gtx 1080 ti in the style of <s0><s1> |
| | output: |
| | url: image-38.png |
| | - text: rapids logo with purple letters in the style of <s0><s1> |
| | output: |
| | url: image-39.png |
| | - text: pandas logo on a black background in the style of <s0><s1> |
| | output: |
| | url: image-40.png |
| | - text: the plotly logo with a blue and white square in the style of <s0><s1> |
| | output: |
| | url: image-41.png |
| | - text: the icon for the app is a bar with three dots in the style of <s0><s1> |
| | output: |
| | url: image-42.png |
| | - text: the logo for postman, a company that delivers packages in the style of <s0><s1> |
| | output: |
| | url: image-43.png |
| | - text: a computer with a lightning bolt on it in the style of <s0><s1> |
| | output: |
| | url: image-44.png |
| | - text: python logo with two snakes on it in the style of <s0><s1> |
| | output: |
| | url: image-45.png |
| | - text: pytorch - a machine learning framework for deep learning in the style of <s0><s1> |
| | output: |
| | url: image-46.png |
| | - text: the logo for firefox in the style of <s0><s1> |
| | output: |
| | url: image-47.png |
| | - text: a purple hexagon with a lightning bolt on it in the style of <s0><s1> |
| | output: |
| | url: image-48.png |
| | - text: a pixelated blue star with a circle in the middle in the style of <s0><s1> |
| | output: |
| | url: image-49.png |
| | - text: the papers app logo in the style of <s0><s1> |
| | output: |
| | url: image-50.png |
| | - text: a drone with an ecg on it in the style of <s0><s1> |
| | output: |
| | url: image-51.png |
| | - text: solikit learn logo in the style of <s0><s1> |
| | output: |
| | url: image-52.png |
| | - text: the s logo in a circle with a blue, orange and green color in the style of |
| | <s0><s1> |
| | output: |
| | url: image-53.png |
| | - text: the logo for the company is colorful in the style of <s0><s1> |
| | output: |
| | url: image-54.png |
| | - text: spacy logo in the style of <s0><s1> |
| | output: |
| | url: image-55.png |
| | - text: the logo for the company is orange and white in the style of <s0><s1> |
| | output: |
| | url: image-56.png |
| | - text: a red crown icon on a black background in the style of <s0><s1> |
| | output: |
| | url: image-57.png |
| | - text: a red crown icon on a black background in the style of <s0><s1> |
| | output: |
| | url: image-58.png |
| | - text: a blue arrow pointing down on a black background in the style of <s0><s1> |
| | output: |
| | url: image-59.png |
| | - text: the t logo with an orange and black background in the style of <s0><s1> |
| | output: |
| | url: image-60.png |
| | - text: the blue x symbol on a black background in the style of <s0><s1> |
| | output: |
| | url: image-61.png |
| | - text: w & b logo in the style of <s0><s1> |
| | output: |
| | url: image-62.png |
| | - text: a lock with arrows pointing to it in the style of <s0><s1> |
| | output: |
| | url: image-63.png |
| | base_model: stabilityai/stable-diffusion-xl-base-1.0 |
| | instance_prompt: in the style of <s0><s1> |
| | license: openrail++ |
| | --- |
| | |
| | # SDXL LoRA DreamBooth - dber123/lora-logo-simple |
| |
|
| | <Gallery /> |
| |
|
| | ## Model description |
| |
|
| | ### These are dber123/lora-logo-simple 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 **[`lora-logo-simple.safetensors` here 💾](/dber123/lora-logo-simple/blob/main/lora-logo-simple.safetensors)**. |
| | - Place it on your `models/Lora` folder. |
| | - On AUTOMATIC1111, load the LoRA by adding `<lora:lora-logo-simple:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/). |
| | - *Embeddings*: download **[`lora-logo-simple_emb.safetensors` here 💾](/dber123/lora-logo-simple/blob/main/lora-logo-simple_emb.safetensors)**. |
| | - Place it on it on your `embeddings` folder |
| | - Use it by adding `lora-logo-simple_emb` to your prompt. For example, `in the style of lora-logo-simple_emb` |
| | (you need both the LoRA and the embeddings as they were trained together for this LoRA) |
| | |
| | |
| | ## Use it with the [🧨 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('dber123/lora-logo-simple', weight_name='pytorch_lora_weights.safetensors') |
| | embedding_path = hf_hub_download(repo_id='dber123/lora-logo-simple', filename='lora-logo-simple_emb.safetensors' repo_type="model") |
| | state_dict = load_file(embedding_path) |
| | pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer) |
| | pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2) |
| | |
| | image = pipeline('in the style of <s0><s1>').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` → use `<s0><s1>` in your prompt |
| |
|
| |
|
| |
|
| | ## Details |
| | All [Files & versions](/dber123/lora-logo-simple/tree/main). |
| |
|
| | The weights were trained using [🧨 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. |
| |
|
| |
|
