Blib-la
/

soda_can_lora_sdxl

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,160 @@

+---
+tags:
+- text-to-image
+- stable-diffusion
+- lora
+- diffusers
+- template:sd-lora
+widget:
+- text: >-
+    a can of "BLIBLA", with exciting colors, rusted and dim lighting
+    <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00007-4104990849.png
+- text: >-
+    a can of "BLIBLA", with vibrant colors, plain background and optimal
+    lighting <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00032-388743413.png
+- text: >-
+    a can of "Acid Rain", with exciting colors, green background and bright
+    lighting <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00069-2760974221.png
+- text: >-
+    a can of "Crazy Juice", with exciting colors, condensation and dim lighting
+    <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00091-2669279066.png
+- text: >-
+    a can of "SDXL", with exciting colors, rusted and colorful lighting
+    <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00089-2669279064.png
+- text: >-
+    a can of "Stable Diffusion", with vibrant colors, plain background and dim
+    lighting <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00131-4140798924.png
+- text: >-
+    a can of "troll juice", with pale colors, intricate design and colorful
+    lighting <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00129-4140798922.png
+- text: >-
+    a can of "unicorn puke", with vibrant colors, intricate design and neon
+    lighting <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00170-3311476337.png
+- text: >-
+    a can of "Meat Juice", with pale colors, comic graphics and professional
+    lighting <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00341-4049900463.png
+- text: >-
+    a can of "Egg White", with pale colors, comic graphics and dark lighting
+    <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00344-2643367320.png
+- text: >-
+    a can of "fish tank", with vibrant colors, intricate design and optimal
+    lighting <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00345-2643367321.png
+- text: >-
+    a can of "Teddy Beer", with pale colors, crushed and colorful lighting
+    <lora:soda_can_sdxl_v1:1>
+  output:
+    url: images/00373-2701734220.png
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: a can of "..."
+license: cc-by-nc-nd-4.0
+---
+# Soda Can LoRA SDXL
+<Gallery />
+## Model description
+# Soda Cans LoRA SDXL
+[![Discord](https:&#x2F;&#x2F;img.shields.io&#x2F;discord&#x2F;1091306623819059300?color&#x3D;7289da&amp;label&#x3D;Discord&amp;logo&#x3D;discord&amp;logoColor&#x3D;fff&amp;style&#x3D;for-the-badge)](https:&#x2F;&#x2F;discord.com&#x2F;invite&#x2F;m3TBB9XEkb)
+## Model Overview
+This model card introduces the LoRA (Low-Rank Adaptation) model trained on the Soda Can Dataset, sourced from our [Soda Can Dataset](https:&amp;#x2F;&amp;#x2F;huggingface.co&amp;#x2F;datasets&amp;#x2F;Blib-la&amp;#x2F;soda_can_dataset). The model excels in generating high-fidelity images of soda cans under various conditions and settings.
+## Training Configuration
+- **Dataset**: [Soda Can Dataset](https:&amp;#x2F;&amp;#x2F;huggingface.co&amp;#x2F;datasets&amp;#x2F;Blib-la&amp;#x2F;soda_can_dataset)
+- **Epochs**: 10
+- **Number of Images**: 200
+- **Repeats per Image**: 10 (Each image was used 10 times during training)
+- **Optimizer**: DAdaptAdam (Tailored for efficient and impactful AI model training)
+- **Precision**: bf16 (Optimized balance between performance and memory efficiency)
+- **Main Trigger**: Fine-tuned to generate diverse soda can images.
+- **Xformers**: Enabled (For enhanced transformer model efficiency)
+- **Captioning Method**: GPT-Vision (Generates descriptive captions for training images, optimized for token shuffling)
+- **Base Model**: Stable Diffusion XL 1.0 (Leverages the robust image generation capabilities of Stable Diffusion XL 1.0)
+## Model Usage
+Specifically trained to generate a wide array of soda can images, this LoRA model can cater to creative, educational, and marketing needs.
+## Performance and Limitations
+- **Performance**: Shows strong capability in rendering soda cans with varied designs and in different contexts.
+- **Limitations**: Given the dataset size of 200 images, the model might exhibit limitations in generating highly unique can designs not represented in the training set.
+## Ethical Considerations
+- **Intended Use**: Aimed at non-commercial applications, including creative design, educational projects, and marketing visualization.
+- **Bias and Fairness**: Users should be cautious of potential dataset biases towards certain brands or can designs.
+## Licensing
+- **Model License**: Licensed under Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND 4.0) for non-commercial use.
+## Contributions and Feedback
+Feedback and contributions to enhance the model are encouraged. For suggestions or contributions to the model&#39;s development, please connect through the model&#39;s Hugging Face page.
+## Trigger words
+Use &#x60;a can of &quot;...&quot;&#x60; to prompt the image generation process.
+## Download model
+The model&#39;s weights are available in Safetensors format for download.
+[Download](&#x2F;Blib-la&#x2F;soda_cans_lora_sdxl&#x2F;tree&#x2F;main) them in the Files &amp; versions tab.
+## Related
+https:&#x2F;&#x2F;blib.la&#x2F;blog&#x2F;reimagining-ai-in-design-bliblas-approach-to-model-training
+## Additional Usage Restrictions for Blibla&#39;s LoRAs Hosted on Hugging Face
+In line with our commitment to ethical use, and in addition to the CC BY-NC 4.0 license, we impose specific restrictions:
+1. **Prohibited Platforms**: Redistribution, reuploading, or image generation services using our models on platforms not aligned with Blibla or Hugging Face&#39;s operations are forbidden. This includes platforms hosting or promoting NSFW content.
+2. **Explicitly Forbidden Platforms**: Specifically, platforms such as Leonardo AI, Civit AI, and any &quot;Hugging Face spaces&quot; allowing NSFW content are barred from using Blibla&#39;s LoRAs.
+3. **User Responsibility**: Users must ensure their use of Blibla&#39;s LoRAs complies with these restrictions. Violations may lead to license revocation and potential legal action.
+4. **Restrictions&#39; Purpose**: These are in place to uphold Blibla&#39;s ethical standards, preventing misuse or harmful associations of our models.
+By using Blibla&#39;s LoRAs, users acknowledge and agree to adhere to these restrictions, promoting responsible and ethical AI use.
+## Trigger words
+You should use `a can of &quot;...&quot;` to trigger the image generation.
+## Download model
+Weights for this model are available in Safetensors format.
+[Download](/Blib-la/soda_can_lora_sdxl_v1/tree/main) them in the Files & versions tab.