400GB-LoraXL

🌌 FFusion's Universe of LoRA Models for Hugging Face 🌠

Welcome to the FFusion LoRA extracted models repository on Hugging Face! Here, we present a collection of models extracted using the Low-Rank Adaptation (LoRA) technique to provide a rich dataset for research and further exploration.

LoRA 66-98 Specifications

📦 Base Models

The following models served as the foundation for our extractions:

• stabilityai/stable-diffusion-xl-base-1.0
• stabilityai/stable-diffusion-xl-base-0.9
• FFusion/FFusionXL-BASE

🌟 Recommended Models for Inference

For those on the quest for ideal models to drive their inference tasks, we especially recommend:

• FFusionXL-BASE - Our signature base model, meticulously trained with licensed images.
• FFXL400 Combined LoRA Model 🚀 - A galactic blend of power and precision in the world of LoRA models.

Rest assured, our LoRAs, even at weight 1.0, maintain compatibility with most of the current SDXL models.

🔍 Extraction Details

• 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 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.

⚙️ 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.
• An important note for users: all models saved with Comfy add an extra key text_model.encoder.text_model.embeddings.position_ids. We've made necessary adjustments to ensure compatibility with the current scripts from Kohoya.

📈 Use Cases

These extracted models are intended for research and testing. They can be particularly useful for:

• 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.

FFusion LoRA Extracted Models - How to Use Guide 🧠

Welcome to the technical guide for using the FFusion LoRA extracted models. This document will walk you through the steps required to fuse LoRA parameters, load checkpoints, and perform inference.

Fusing LoRA Parameters 🔗

To merge the LoRA parameters with the original parameters of the underlying model(s), leading to a potential speedup in inference latency:

pipe.fuse_lora()

Unfusing LoRA Parameters ⛓️

To revert the effects of fuse_lora():

pipe.unfuse_lora()

Working with Different LoRA Scales 🎚️

To control the influence of the LoRA parameters on the outputs:

pipe.fuse_lora(lora_scale=0.5)

Working with FFusion Models 🔍

Here's how to load and utilize our FFusion models:

from diffusers import DiffusionPipeline
import torch

pipeline_id = "FFusion/FFusionXL-BASE"

pipe = DiffusionPipeline.from_pretrained(pipeline_id, torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()

lora_model_id = "FFusion/400GB-LoraXL"
lora_filename = "FFai.0038.Realitycheckxl_Alpha11.lora.safetensors"
pipe.load_lora_weights(lora_model_id, weight_name=lora_filename)

prompt = "papercut sonic"
image = pipe(prompt=prompt, num_inference_steps=20, generator=torch.manual_seed(0)).images[0]
image

Running Inference 🖼️

After loading the desired model, you can perform inference as follows:

generator = torch.manual_seed(0)
images_fusion = pipe(
    - "masterpiece, best quality, mountain", output_type="np", generator=generator, num_inference_steps=25
).images

⚠️ License & Usage Disclaimers

Please review the full license agreement before accessing or using the models.

🔴 The models and weights available in this repository are strictly for research and testing purposes, with exceptions noted below. They are not generally intended for commercial use and are dependent on each individual LORA.

🔵 Exception for Commercial Use: The FFusionXL-BASE, FFusion-BaSE, di.FFUSION.ai-v2.1-768-BaSE-alpha, and di.ffusion.ai.Beta512 models are trained by FFusion AI using images for which we hold licenses. Users are advised to primarily use these models for a safer experience. These particular models are allowed for commercial use.

🔴 Disclaimer: FFusion AI, in conjunction with Source Code Bulgaria Ltd and BlackswanTechnologies, does not endorse or guarantee the content produced by the weights in each LORA. There's potential for generating NSFW or offensive content. Collectively, we expressly disclaim responsibility for the outcomes and content produced by these weights.

🔴 Acknowledgement: The FFusionXL-BASE model model is a uniquely developed version by FFusion AI. Rights to this and associated modifications belong to FFusion AI and Source Code Bulgaria Ltd. Ensure adherence to both this license and any conditions set by Stability AI Ltd for referenced models.

Library of Available LoRA Models 📚

You can choose any of the models from our repository on Hugging Face or the upcoming repository on CivitAI. Here's a list of available models with lora_model_id = "FFusion/400GB-LoraXL":

lora_filename = 
    - FFai.0001.4Guofeng4xl_V1125d.lora_Dim64.safetensors
    - FFai.0002.4Guofeng4xl_V1125d.lora_Dim8.safetensors
    - FFai.0003.4Guofeng4xl_V1125d.loraa.safetensors
    - FFai.0004.Ambiencesdxl_A1.lora.safetensors
    - FFai.0005.Ambiencesdxl_A1.lora_8.safetensors
    - FFai.0006.Angrasdxl10_V22.lora.safetensors
    - FFai.0007.Animaginexl_V10.lora.safetensors
    - FFai.0008.Animeartdiffusionxl_Alpha3.lora.safetensors
    - FFai.0009.Astreapixiexlanime_V16.lora.safetensors
    - FFai.0010.Bluepencilxl_V010.lora.safetensors
    - FFai.0011.Bluepencilxl_V021.lora.safetensors
    - FFai.0012.Breakdomainxl_V03d.lora.safetensors
    - FFai.0013.Canvasxl_Bfloat16v002.lora.safetensors
    - FFai.0014.Cherrypickerxl_V20.lora.safetensors
    - FFai.0015.Copaxtimelessxlsdxl1_V44.lora.safetensors
    - FFai.0016.Counterfeitxl-Ffusionai-Alpha-Vae.lora.safetensors
    - FFai.0017.Counterfeitxl_V10.lora.safetensors
    - FFai.0018.Crystalclearxl_Ccxl.lora.safetensors
    - FFai.0019.Deepbluexl_V006.lora.safetensors
    - FFai.0020.Dream-Ffusion-Shaper.lora.safetensors
    - FFai.0021.Dreamshaperxl10_Alpha2xl10.lora.safetensors
    - FFai.0022.Duchaitenaiartsdxl_V10.lora.safetensors
    - FFai.0023.Dynavisionxlallinonestylized_Beta0371bakedvae.lora.safetensors
    - FFai.0024.Dynavisionxlallinonestylized_Beta0411bakedvae.lora.safetensors
    - FFai.0025.Fantasticcharacters_V55.lora.safetensors
    - FFai.0026.Fenrisxl_V55.lora.safetensors
    - FFai.0027.Fudukimix_V10.lora.safetensors
    - FFai.0028.Infinianimexl_V16.lora.safetensors
    - FFai.0029.Juggernautxl_Version1.lora_1.safetensors
    - FFai.0030.Lahmysterioussdxl_V330.lora.safetensors
    - FFai.0031.Mbbxlultimate_V10rc.lora.safetensors
    - FFai.0032.Miamodelsfwnsfwsdxl_V30.lora.safetensors
    - FFai.0033.Morphxl_V10.lora.safetensors
    - FFai.0034.Nightvisionxlphotorealisticportrait_Beta0681bakedvae.lora_1.safetensors
    - FFai.0035.Osorubeshialphaxl_Z.lora.safetensors
    - FFai.0036.Physiogenxl_V04.lora.safetensors
    - FFai.0037.Protovisionxlhighfidelity3d_Beta0520bakedvae.lora.safetensors
    - FFai.0038.Realitycheckxl_Alpha11.lora.safetensors
    - FFai.0039.Realmixxl_V10.lora.safetensors
    - FFai.0040.Reproductionsdxl_V31.lora.safetensors
    - FFai.0041.Rundiffusionxl_Beta.lora.safetensors
    - FFai.0042.Samaritan3dcartoon_V40sdxl.lora.safetensors
    - FFai.0043.Sdvn6realxl_Detailface.lora.safetensors
    - FFai.0044.Sdvn7realartxl_Beta2.lora.safetensors
    - FFai.0045.Sdxl10arienmixxlasian_V10.lora.safetensors
    - FFai.0046.Sdxlbasensfwfaces_Sdxlnsfwfaces03.lora.safetensors
    - FFai.0047.Sdxlfaetastic_V10.lora.safetensors
    - FFai.0048.Sdxlfixedvaefp16remove_Basefxiedvaev2fp16.lora.safetensors
    - FFai.0049.Sdxlnijiv4_Sdxlnijiv4.lora.safetensors
    - FFai.0050.Sdxlronghua_V11.lora.safetensors
    - FFai.0051.Sdxlunstablediffusers_V5unchainedslayer.lora.safetensors
    - FFai.0052.Sdxlyamersanimeultra_Yamersanimev2.lora.safetensors
    - FFai.0053.Shikianimexl_V10.lora.safetensors
    - FFai.0054.Spectrumblendx_V10.lora.safetensors
    - FFai.0055.Stablediffusionxl_V30.lora.safetensors
    - FFai.0056.Talmendoxlsdxl_V11beta.lora.safetensors
    - FFai.0057.Wizard_V10.lora.safetensors
    - FFai.0058.Wyvernmix15xl_Xlv11.lora.safetensors
    - FFai.0059.Xl13asmodeussfwnsfw_V17bakedvae.lora.safetensors
    - FFai.0060.Xl3experimentalsd10xl_V10.lora.safetensors
    - FFai.0061.Xl6hephaistossd10xlsfw_V21bakedvaefp16fix.lora.safetensors
    - FFai.0062.Xlperfectdesign_V2ultimateartwork.lora.safetensors
    - FFai.0063.Xlyamersrealistic_V3.lora.safetensors
    - FFai.0064.Xxmix9realisticsdxl_Testv20.lora.safetensors
    - FFai.0065.Zavychromaxl_B2.lora.safetensors
    - FF.66.hassakuSfwNsfwAlphav_alphaV02.lora.safetensors
    - FF.67.galaxytimemachinesGTM_xlplusV10.lora.safetensors
    - FF.68.furtasticxl_BetaEPOCHS3.lora.safetensors
    - FF.69.formulaxlXLComfyui_v20Pruned.lora.safetensors
    - FF.70.FinalAnimeCG_mk2a2.lora.safetensors
    - FF.71.explicitFreedomNSFW_beta.lora.safetensors
    - FF.72.endjourneyXL_v11.lora.safetensors
    - FF.73.dreamshaperXL10_alpha2Xl10.lora.safetensors
    - FF.74.copaxTimelessxlSDXL1_v5.lora.safetensors
    - FF.75.cinemaxAlphaSDXLCinema_alpha1.lora.safetensors
    - FF.76.brixlAMustInYour_v20Banu.lora.safetensors
    - FF.77.animeChangefulXL_v10ReleasedCandidate.lora.safetensors
    - FF.78.xlYamersCartoonArcadia_v1.lora.safetensors
    - FF.79.venusxl_v11.lora.safetensors
    - FF.80.unsafexl_v20.lora.safetensors
    - FF.81.sdxlYamersRealism_version2.lora.safetensors
    - FF.82.sdxlUnstableDiffusers_v6StabilityEater.lora.safetensors
    - FF.83.sdxlNuclearGeneralPurposeSemi_v10.lora.safetensors
    - FF.84.sdvn6Realxl_detailface.lora.safetensors
    - FF.85.samaritan3dCartoon_v40SDXL.lora.safetensors
    - FF.86.realvisxlV10_v10VAE.lora.safetensors
    - FF.87.RealitiesEdgeXLANIME_20.lora.safetensors
    - FF.88.RealitiesEdgeXL_30.lora.safetensors
    - FF.89.realisticStockPhoto_v10.lora.safetensors
    - FF.90.realisticFreedomSFW_alpha.lora.safetensors
    - FF.91.realcartoonXL_v2.lora.safetensors
    - FF.92.pyrosSDModelsBlowjob_v0122022steps.lora.safetensors
    - FF.93.pyrosNSFWSDXL_v013e6.lora.safetensors
    - FF.94.nightvisionXLPhotorealisticPortrait_v0743ReleaseBakedvae.lora.safetensors
    - FF.95.newone_v10.lora.safetensors
    - FF.96.MOHAWK_v10BETA.lora.safetensors
    - FF.97.juggernautXL_version4.lora.safetensors
    - FF.98.sdxlYamersRealism_version2.lora.safetensors

📊 Text Encoder Difference Overview

Based on the extraction process, we observed the following differences in the text encoder across various models:

• bluePencilXL_v021 ✅ Text encoder available. Difference by 0.00140380859375
• sdvn7Realartxl_beta2 ✅ Text encoder available. Difference by 0.00362396240234375
• 4Guofeng4XL_v1125D 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• ambienceSDXL_a1 ✅ Text encoder available. Difference by 0.003082275390625
• angraSDXL10_v22 ✅ Text encoder available. Difference by 0.001953125
• animagineXL_v10 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• animeArtDiffusionXL_alpha3 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• astreapixieXLAnime_v16 ✅ Text encoder available. Difference by 0.0029296875
• bluePencilXL_v010 ✅ Text encoder available. Difference by 0.00177001953125
• breakdomainxl_v03d ✅ Text encoder available. Difference by 0.0013427734375
• canvasxl_Bfloat16V002 ✅ Text encoder available. Difference by 0.00390625
• cherryPickerXL_v20 ✅ Text encoder available. Difference by 0.0016450881958007812
• copaxTimelessxlSDXL1_v44 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• counterfeitxl_v10 ✅ Text encoder available. Difference by 0.001708984375
• crystalClearXL_ccxl ✅ Text encoder available. Difference by 0.0012865066528320312
• deepblueXL_v006 ✅ Text encoder available. Difference by 0.00200653076171875
• dreamshaperXL10_alpha2Xl10 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• duchaitenAiartSDXL_v10 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• dynavisionXLAllInOneStylized_beta0371Bakedvae ✅ Text encoder available. Difference by 0.00321197509765625
• dynavisionXLAllInOneStylized_beta0411Bakedvae ✅ Text encoder available. Difference by 0.0037841796875
• envyoverdrivexl_v11 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• envypoodaxl01_v10 ✅ Text encoder available. Difference by 0.0011358261108398438
• fantasticCharacters_v55 ✅ Text encoder available. Difference by 0.00390625
• fenrisxl_V55 ✅ Text encoder available. Difference by 0.0086822509765625
• fudukiMix_v10 ✅ Text encoder available. Difference by 0.0011138916015625
• infinianimexl_v16 ✅ Text encoder available. Difference by 0.0048828125
• juggernautXL_version1 ✅ Text encoder available. Difference by 0.001953125
• LahMysteriousSDXL_v330 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• mbbxlUltimate_v10RC 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• miamodelSFWNSFWSDXL_v30 ✅ Text encoder available. Difference by 0.0047607421875
• morphxl_v10 ✅ Text encoder available. Difference by 0.001861572265625
• nightvisionXLPhotorealisticPortrait_beta0681Bakedvae ✅ Text encoder available. Difference by 0.013885498046875
• osorubeshiAlphaXL_z ✅ Text encoder available. Difference by 0.005615234375
• physiogenXL_v04 ✅ Text encoder available. Difference by 0.00390625
• protovisionXLHighFidelity3D_beta0520Bakedvae ✅ Text encoder available. Difference by 0.007568359375
• realitycheckXL_alpha11 ✅ Text encoder available. Difference by 0.0015010833740234375
• realmixXL_v10 ✅ Text encoder available. Difference by 0.0023899078369140625
• reproductionSDXL_v31 ✅ Text encoder available. Difference by 0.00146484375
• rundiffusionXL_beta ✅ Text encoder available. Difference by 0.00196075439453125
• samaritan3dCartoon_v40SDXL ✅ Text encoder available. Difference by 0.0009765625
• sdvn6Realxl_detailface 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• sdxl10ArienmixxlAsian_v10 ✅ Text encoder available. Difference by 0.00048828125
• sdxlbaseNsfwFaces_sdxlNsfwFaces03 ✅ Text encoder available. Difference by 0.008056640625
• sdxlFaetastic_v10 ✅ Text encoder available. Difference by 0.0029296875
• sdxlFixedvaeFp16Remove_baseFxiedVaeV2Fp16 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• sdxlNijiV4_sdxlNijiV4 ✅ Text encoder available. Difference by 0.0009765625
• SDXLRonghua_v11 ✅ Text encoder available. Difference by 0.0009765625
• sdxlUnstableDiffusers_v5UnchainedSlayer ✅ Text encoder available. Difference by 0.001251220703125
• sdxlYamersAnimeUltra_yamersAnimeV2 ✅ Text encoder available. Difference by 0.000732421875
• sdXL_v10VAEFix 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• shikianimexl_v10 ✅ Text encoder available. Difference by 0.0009765625
• spectrumblendx_v10 ✅ Text encoder available. Difference by 0.0013065338134765625
• stableDiffusionXL_v30 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• talmendoxlSDXL_v11Beta 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• wizard_v10 ✅ Text encoder available. Difference by 0.000244140625
• sdxlYamersRealism_version2 - ✅ Text encoder available. Difference by 0.0048828125
• animeChangefulXL_v10ReleasedCandidate - ✅ Text encoder available. Difference by 0.00390625
• brixlAMustInYour_v20Banu - ✅ Text encoder available. Difference by 0.001434326171875
• cinemaxAlphaSDXLCinema_alpha1 - ✅ Text encoder available. Difference by 0.00311279296875
• copaxTimelessxlSDXL1_v5 - 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• dreamshaperXL10_alpha2Xl10 - 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• endjourneyXL_v11 - ✅ Text encoder available. Difference by 0.0029296875
• explicitFreedomNSFW_beta - ✅ Text encoder available. Difference by 0.001220703125
• FinalAnimeCG_mk2a2 - ✅ Text encoder available. Difference by 0.00390625
• formulaxlXLComfyui_v20Pruned - ✅ Text encoder available. Difference by 0.002643585205078125
• furtasticxl_BetaEPOCHS3 - ✅ Text encoder available. Difference by 0.013824462890625
• galaxytimemachinesGTM_xlplusV10 - ✅ Text encoder available. Difference by 0.0012865066528320312
• hassakuSfwNsfwAlphav_alphaV02 - ✅ Text encoder available. Difference by 0.00390625
• juggernautXL_version4 - ✅ Text encoder available. Difference by 0.0019378662109375
• MOHAWK_v10BETA - ✅ Text encoder available. Difference by 0.00103759765625
• newone_v10 - ✅ Text encoder available. Difference by 0.001190185546875
• nightvisionXLPhotorealisticPortrait_v0743ReleaseBakedvae - ✅ Text encoder available. Difference by 0.009429931640625
• pyrosNSFWSDXL_v013e6 - 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• pyrosSDModelsBlowjob_v0122022steps - 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• realisticFreedomSFW_alpha - ✅ Text encoder available. Difference by 0.0011749267578125
• realisticStockPhoto_v10 - ✅ Text encoder available. Difference by 0.0011444091796875
• RealitiesEdgeXLANIME_20 - ✅ Text encoder available. Difference by 0.0018310546875
• RealitiesEdgeXL_30 - ✅ Text encoder available. Difference by 0.004150390625
• realvisxlV10_v10VAE - ✅ Text encoder available. Difference by 0.0029296875
• samaritan3dCartoon_v40SDXL - ✅ Text encoder available. Difference by 0.00390625
• sdvn6Realxl_detailface - 🚫 Text encoder unavailable. Same as SDXL 1.0 Base
• sdxlNuclearGeneralPurposeSemi_v10 - ✅ Text encoder available. Difference by 0.003021240234375
• sdxlUnstableDiffusers_v6StabilityEater - ✅ Text encoder available. Difference by 0.0029296875
• sdxlYamersRealism_version2 - ✅ Text encoder available. Difference by 0.0048828125
• unsafexl_v20 - ✅ Text encoder available. Difference by 0.068359375
• venusxl_v11 - ✅ Text encoder available. Difference by 0.0013863444328308105
• xlYamersCartoonArcadia_v1 - ✅ Text encoder available. Difference by 0.0029296875

🎉 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 for our work.
• kohya-ss/sd-scripts and bmaltais: Our work also incorporates modifications from kohya-ss/sd-scripts.
• lora-inspector: We've benefited from the lora-inspector project.
• KohakuBlueleaf: Special mention to KohakuBlueleaf for their invaluable contributions.

HowMuch ???

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

From PyPI

You can easily install HowMuch via pip:

pip install howmuch

From Source

1. Clone the repository:

   git clone https://github.com/1e-2/HowMuch.git
   

2. Navigate to the cloned directory and install:

   cd HowMuch
   pip install .
   

Usage

Run the tool without any arguments to scan all drives:

howmuch

Or, specify a particular directory or drive to scan:

howmuch --scan C:

🌐 Contact Information

The FFusion.ai project is proudly maintained by Source Code Bulgaria Ltd & Black Swan Technologies.

📧 Reach us at [email protected] for any inquiries or support.

🌌 Find us on:

• 🐙 GitHub
• 😊 Hugging Face
• 💡 Civitai

🔐 Security powered by Comodo.BG & Preasidium.CX 🚀 Marketing by Гугъл.com 📩 🌍 Sofia Istanbul London