xyz samples

README.md

@@ -3,10 +3,10 @@ license: openrail++
 base_model: stabilityai/stable-diffusion-xl-base-1.0
 instance_prompt: FF00
 widget:
-  - text: a dog playing in the sand, digital art animal photo,  anime artwork
+  - text: a dog playing in the sand, digital art animal photo, anime artwork
 tags:
 - stable-diffusion-xl
-- stable-diffusion-xl-diffusers
+- diffusers
 - stable-diffusion
 - text-to-image
 - lora
@@ -18,7 +18,7 @@ thumbnail: >-
   https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image0thumb.jpg
 library_name: diffusers
 ---
-[![400GB FFusion Lora XL 1](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image1sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image0.jpg)
+[![400GB FFusion Lora XL 1](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image0.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/tree/main)
 
 # FFusion LoRA Extracted Models for Hugging Face 🚀
 
@@ -37,9 +37,11 @@ The following models served as the foundation for our extractions:
 - **Variants:** Each base model was extracted into 4-5 distinct variants.
 - **Extraction Depth:** The models uploaded here contain approximately 70% of extracted data. These extractions yield a dataset size of around 400 GB.
 - **Precision:** We experimented with both `float32` and `float64` for optimal extraction results.
-- **Differences Measurement:** Singular Value Decomposition (SVD) was utilized to measure differences between the original and the tuned models. A threshold of \(1 \times 10^{-3}\) was commonly used, although in some cases, \(1 \times 10^{-5}\) and \(1 \times 10^{-2}\) were tested.
+- **Differences Measurement:** Singular Value Decomposition (SVD) was utilized to measure differences between the original and the tuned models. A threshold of 1e-3 was commonly used, although in some cases, 1e-5 and 1e-2 were tested.
 - **Demonstration Parameters:** For our demonstration, we employed `"conv_dim": 256` and `"conv_alpha": 256`.
 
+[![400GB FFusion Lora XL 8](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image8sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image8.jpg)
+
 ## ⚙️ Technical Notes
 
 - Most SDXL models in this collection are not traditionally "trained." Instead, they are merged from previous SDXL 0.9 versions or created using other methods with the help of Comfy UI.
@@ -52,18 +54,7 @@ These extracted models are intended for research and testing. They can be partic
 - Investigating the potential of merging multiple LoRAs.
 - Weighting experiments with 1-5 LoRAs simultaneously.
 - Exploring the differences and similarities between LoRAs extracted from different base models.
-
-## 🎉 Acknowledgements & Citations
-
-A huge shoutout to the community for their continued support and feedback. Together, we are pushing the boundaries of what's possible with machine learning!
-
-We would also like to acknowledge and give credit to the following projects and authors:
-
-- **ComfyUI**: We've used and modified portions of [ComfyUI](https://github.com/comfyanonymous/ComfyUI) for our work.
-- **kohya-ss/sd-scripts and bmaltais**: Our work also incorporates modifications from [kohya-ss/sd-scripts](https://github.com/kohya-ss/sd-scripts).
-- **lora-inspector**: We've benefited from the [lora-inspector](https://github.com/rockerBOO/lora-inspector) project.
-- **KohakuBlueleaf**: Special mention to KohakuBlueleaf for their invaluable contributions.
-
+[![400GB FFusion Lora XL 2](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image2sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image2.jpg)
 
 # FFusion LoRA Extracted Models - How to Use Guide 🧠
 
@@ -200,200 +191,148 @@ lora_filename =
 
 ```
 
-📊 Text Encoder Difference Overview
+### 📊 Text Encoder Difference Overview
 Based on the extraction process, we observed the following differences in the text encoder across various models:
 
-## 4Guofeng4XL_v1125D
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## AmbienceSDXL_a1
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **4Guofeng4XL_v1125D** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## angraSDXL10_v22
-✅ Text encoder available. Difference by 0.001953125
+- **AmbienceSDXL_a1 ** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## animagineXL_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **angraSDXL10_v22** ✅ Text encoder available. Difference by 0.001953125
 
-## animeArtDiffusionXL_alpha3
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **animagineXL_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## AstreaPixieXLAnime_v16
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **animeArtDiffusionXL_alpha3** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## bluePencilXL_v010
-✅ Text encoder available. Difference by 0.001953125
+- **AstreaPixieXLAnime_v16** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## bluePencilXL_v021
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **bluePencilXL_v010 ** ��� Text encoder available. Difference by 0.001953125
 
-## breakdomainXL_v03d
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **bluePencilXL_v021 ** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## canvasXL_bFloat16v002
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **breakdomainXL_v03d** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## cherryPickerXL_v20
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **canvasXL_bFloat16v002** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## copaXTimelessXLSDXL1_v44
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **cherryPickerXL_v20** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## counterfeitXL-FFusionAI-alpha-VAE
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **copaXTimelessXLSDXL1_v44** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## counterfeitXL_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **counterfeitXL-FFusionAI-alpha-VAE** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## crystalclearXL_ccxl
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **counterfeitXL_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## deepblueXL_v006
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **crystalclearXL_ccxl** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## dream-FFusion-shaper
-✅ Text encoder available. Difference by 0.001953125
+- **deepblueXL_v006** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## dreamShaperXL10_alpha2xl10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **dream-FFusion-shaper** ✅ Text encoder available. Difference by 0.001953125
 
-## duchaitenaiartsSDXL_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **dreamShaperXL10_alpha2xl10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## dynavisionXLallInOneStylized_beta0371bakedVAE
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **duchaitenaiartsSDXL_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## dynavisionXLallInOneStylized_beta0411bakedVAE
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **dynavisionXLallInOneStylized_beta0371bakedVAE** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## fantasticCharacters_v55
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **dynavisionXLallInOneStylized_beta0411bakedVAE** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## fenrisXL_v55
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **fantasticCharacters_v55** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## fudukimix_v10
-✅ Text encoder available. Difference by 0.001953125
+- **fenrisXL_v55** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## infiniaNimeXL_v16
-✅ Text encoder available. Difference by 0.001953125
+- **fudukimix_v10** ✅ Text encoder available. Difference by 0.001953125
 
-## juggernautXL_version1
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **infiniaNimeXL_v16** ✅ Text encoder available. Difference by 0.001953125
 
-## lahMysteriousSDXL_v330
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **juggernautXL_version1** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## mbBXLUltimate_v10rc
-✅ Text encoder available. Difference by 0.001953125
+- **lahMysteriousSDXL_v330** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## miaModelsFWNsfwSDXL_v30
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **mbBXLUltimate_v10rc** ✅ Text encoder available. Difference by 0.001953125
 
-## morphXL_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **miaModelsFWNsfwSDXL_v30** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## nightvisionXLphotorealisticPortrait_beta0681bakedVAE
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **morphXL_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## osorubeshiAlphaXL_z
-✅ Text encoder available. Difference by 0.001953125
+- **nightvisionXLphotorealisticPortrait_beta0681bakedVAE** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## physiogenXL_v04
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **osorubeshiAlphaXL_z** ✅ Text encoder available. Difference by 0.001953125
 
-## protoVisionXLhighFidelity3D_beta0520bakedVAE
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **physiogenXL_v04** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## realityCheckXL_alpha11
-✅ Text encoder available. Difference by 0.001953125
+- **protoVisionXLhighFidelity3D_beta0520bakedVAE** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## realmixXL_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **realityCheckXL_alpha11** ✅ Text encoder available. Difference by 0.001953125
 
-## reproductionSDXL_v31
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **realmixXL_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## runDiffusionXL_beta
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **reproductionSDXL_v31** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## samaritan3DCartoon_v40sdxl
-✅ Text encoder available. Difference by 0.001953125
+- **runDiffusionXL_beta** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## sdvn6realXL_detailFace
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **samaritan3DCartoon_v40sdxl** ✅ Text encoder available. Difference by 0.001953125
 
-## sdvn7realArtXL_beta2
-✅ Text encoder available. Difference by 0.001953125
+- **sdvn6realXL_detailFace** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## sdxl10arienMixXLasian_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **sdvn7realArtXL_beta2** ✅ Text encoder available. Difference by 0.001953125
 
-## sdxlBaseNSFWFaces_sdxlNSFWFaces03
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **sdxl10arienMixXLasian_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## sdxlFaeTastic_v10
-✅ Text encoder available. Difference by 0.001953125
+- **sdxlBaseNSFWFaces_sdxlNSFWFaces03** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## sdxlFixedVAEfp16Remove_baseFxiedVAEv2fp16
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **sdxlFaeTastic_v10** ✅ Text encoder available. Difference by 0.001953125
 
-## sdxlNijiV4_sdxlNijiV4
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **sdxlFixedVAEfp16Remove_baseFxiedVAEv2fp16** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## sdxlRonghua_v11
-✅ Text encoder available. Difference by 0.001953125
+- **sdxlNijiV4_sdxlNijiV4** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## sdxlUnstableDiffusers_v5UnchainedSlayer
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **sdxlRonghua_v11** ✅ Text encoder available. Difference by 0.001953125
 
-## sdxlYamersAnimeUltra_yamersAnimeV2
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **sdxlUnstableDiffusers_v5UnchainedSlayer** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## shikiAnimeXL_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **sdxlYamersAnimeUltra_yamersAnimeV2** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## spectrumBlendX_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **shikiAnimeXL_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## stableDiffusionXL_v30
-✅ Text encoder available. Difference by 0.001953125
+- **spectrumBlendX_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## talMendoXlsdXL_v11beta
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **stableDiffusionXL_v30** ✅ Text encoder available. Difference by 0.001953125
 
-## wizard_v10
-✅ Text encoder available. Difference by 0.001953125
+- **talMendoXlsdXL_v11beta** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## wyvernMix15XL_XLv11
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **wizard_v10** ✅ Text encoder available. Difference by 0.001953125
 
-## xl13asmodeusSFWNSFW_v17bakedVAEfp16fix
-✅ Text encoder available. Difference by 0.001953125
+- **wyvernMix15XL_XLv11** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## xl3experimentalSD10XL_v10
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **xl13asmodeusSFWNSFW_v17bakedVAEfp16fix** ✅ Text encoder available. Difference by 0.001953125
 
-## xl6hephaistosSD10XLsfw_v21bakedVAEfp16fix
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **xl3experimentalSD10XL_v10** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## xlPerfectDesign_v2UltimateArtwork
-✅ Text encoder available. Difference by 0.001953125
+- **xl6hephaistosSD10XLsfw_v21bakedVAEfp16fix** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## xlYamersRealistic_v3
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **xlPerfectDesign_v2UltimateArtwork** ✅ Text encoder available. Difference by 0.001953125
 
-## xxMix9RealisticSDXL_Testv20
-✅ Text encoder available. Difference by 0.001953125
+- **xlYamersRealistic_v3** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
-## zavyChromaXL_b2
-🔴 Text encoder unavailable. Same as SDXL 1.0 Base
+- **xxMix9RealisticSDXL_Testv20** ✅ Text encoder available. Difference by 0.001953125
 
+- **zavyChromaXL_b2** 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
 
 
-[![400GB FFusion Lora XL 1](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image1sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image1.jpg)
+## 🎉 Acknowledgements & Citations
 
-[![400GB FFusion Lora XL 2](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image2sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image2.jpg)
+A huge shoutout to the community for their continued support and feedback. Together, we are pushing the boundaries of what's possible with machine learning!
+
+We would also like to acknowledge and give credit to the following projects and authors:
+
+- **ComfyUI**: We've used and modified portions of [ComfyUI](https://github.com/comfyanonymous/ComfyUI) for our work.
+- **kohya-ss/sd-scripts and bmaltais**: Our work also incorporates modifications from [kohya-ss/sd-scripts](https://github.com/kohya-ss/sd-scripts).
+- **lora-inspector**: We've benefited from the [lora-inspector](https://github.com/rockerBOO/lora-inspector) project.
+- **KohakuBlueleaf**: Special mention to KohakuBlueleaf for their invaluable contributions.
+
+
+[![400GB FFusion Lora XL 1](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image1sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image1.jpg)
 
 [![400GB FFusion Lora XL 3](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image3sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image3.jpg)
 
@@ -405,6 +344,69 @@ Based on the extraction process, we observed the following differences in the te
 
 [![400GB FFusion Lora XL 7](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image7sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image7.jpg)
 
-[![400GB FFusion Lora XL 8](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image8sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image8.jpg)
+[![400GB FFusion Lora XL 9](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image9.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/tree/main)
 
-[![400GB FFusion Lora XL 9](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image9sm.jpg)](https://huggingface.co/FFusion/400GB-LoraXL/resolve/main/images/image9.jpg)
+
+
+
+
+### HowMuch ???
+![60% Works](https://img.shields.io/badge/60%25%20of%20the%20Time-It%20Works%20Every%20Time-green)
+
+
+**Have you ever asked yourself, "How much space have I wasted on `*.ckpt` and `*.safetensors` checkpoints?"** 🤔
+Say hello to HowMuch: Checking checkpoint wasted space since... well, now! 
+
+😄 Enjoy this somewhat unnecessary, yet **"fun-for-the-whole-family"** DiskSpaceAnalyzer tool. 😄
+
+## Overview
+
+
+`HowMuch` is a Python tool designed to scan your drives (or a specified directory) and report on the total space used by files with specific extensions, mainly `.ckpt` and `.safetensors`. 
+
+It outputs:
+- The total storage capacity of each scanned drive or directory.
+- The space occupied by `.ckpt` and `.safetensors` files.
+- The free space available.
+- A neat bar chart visualizing the above data.
+
+## Installation
+[GitHub](https://github.com/1e-2/HowMuch)
+
+### From PyPI
+
+You can easily install `HowMuch` via pip:
+
+```bash
+pip install howmuch
+```
+
+### From Source
+
+1. Clone the repository:
+
+   ```bash
+   git clone https://github.com/1e-2/HowMuch.git
+   ```
+
+2. Navigate to the cloned directory and install:
+
+   ```bash
+   cd HowMuch
+   pip install .
+   ```
+
+## Usage
+
+
+Run the tool without any arguments to scan all drives:
+
+```bash
+howmuch
+```
+
+Or, specify a particular directory or drive to scan:
+
+```bash
+howmuch --scan C:
+```