license: openrail++
base_model: diffusers/stable-diffusion-xl-base-1.0
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- stable-diffusion
- text-to-image
- lora
- loraxl
- di.FFusion.ai
language:
- en
thumbnail: >-
https://cdn-uploads.huggingface.co/production/uploads/6380cf05f496d57325c12194/p54u7dEP1u8en0--NMEjS.png
library_name: diffusers
FFusion LoRA Extracted Models for Hugging Face π
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.
π¦ 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
π 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
andfloat64
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.
- Demonstration Parameters: For our demonstration, we employed
"conv_dim": 256
and"conv_alpha": 256
.
βοΈ 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.
π 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.
π 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.
FFusion LoRA Extracted Models - How to Use Guide π§
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 π
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 βοΈ
To revert the effects of fuse_lora()
:
pipe.unfuse_lora()
Working with Different LoRA Scales ποΈ
To control the influence of the LoRA parameters on the outputs:
pipe.fuse_lora(lora_scale=0.5)
Working with FFusion Models π
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-LoraX"
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 πΌοΈ
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=2
).images
Library of Available LoRA Models π
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
π Text Encoder Difference Overview Based on the extraction process, we observed the following differences in the text encoder across various models:
4Guofeng4XL_v1125D
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
AmbienceSDXL_a1
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
angraSDXL10_v22
β Text encoder available. Difference by 0.001953125
animagineXL_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
animeArtDiffusionXL_alpha3
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
AstreaPixieXLAnime_v16
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
bluePencilXL_v010
β Text encoder available. Difference by 0.001953125
bluePencilXL_v021
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
breakdomainXL_v03d
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
canvasXL_bFloat16v002
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
cherryPickerXL_v20
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
copaXTimelessXLSDXL1_v44
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
counterfeitXL-FFusionAI-alpha-VAE
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
counterfeitXL_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
crystalclearXL_ccxl
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
deepblueXL_v006
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
dream-FFusion-shaper
β Text encoder available. Difference by 0.001953125
dreamShaperXL10_alpha2xl10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
duchaitenaiartsSDXL_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
dynavisionXLallInOneStylized_beta0371bakedVAE
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
dynavisionXLallInOneStylized_beta0411bakedVAE
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
fantasticCharacters_v55
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
fenrisXL_v55
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
fudukimix_v10
β Text encoder available. Difference by 0.001953125
infiniaNimeXL_v16
β Text encoder available. Difference by 0.001953125
juggernautXL_version1
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
lahMysteriousSDXL_v330
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
mbBXLUltimate_v10rc
β Text encoder available. Difference by 0.001953125
miaModelsFWNsfwSDXL_v30
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
morphXL_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
nightvisionXLphotorealisticPortrait_beta0681bakedVAE
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
osorubeshiAlphaXL_z
β Text encoder available. Difference by 0.001953125
physiogenXL_v04
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
protoVisionXLhighFidelity3D_beta0520bakedVAE
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
realityCheckXL_alpha11
β Text encoder available. Difference by 0.001953125
realmixXL_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
reproductionSDXL_v31
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
runDiffusionXL_beta
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
samaritan3DCartoon_v40sdxl
β Text encoder available. Difference by 0.001953125
sdvn6realXL_detailFace
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
sdvn7realArtXL_beta2
β Text encoder available. Difference by 0.001953125
sdxl10arienMixXLasian_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
sdxlBaseNSFWFaces_sdxlNSFWFaces03
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
sdxlFaeTastic_v10
β Text encoder available. Difference by 0.001953125
sdxlFixedVAEfp16Remove_baseFxiedVAEv2fp16
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
sdxlNijiV4_sdxlNijiV4
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
sdxlRonghua_v11
β Text encoder available. Difference by 0.001953125
sdxlUnstableDiffusers_v5UnchainedSlayer
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
sdxlYamersAnimeUltra_yamersAnimeV2
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
shikiAnimeXL_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
spectrumBlendX_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
stableDiffusionXL_v30
β Text encoder available. Difference by 0.001953125
talMendoXlsdXL_v11beta
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
wizard_v10
β Text encoder available. Difference by 0.001953125
wyvernMix15XL_XLv11
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
xl13asmodeusSFWNSFW_v17bakedVAEfp16fix
β Text encoder available. Difference by 0.001953125
xl3experimentalSD10XL_v10
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
xl6hephaistosSD10XLsfw_v21bakedVAEfp16fix
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
xlPerfectDesign_v2UltimateArtwork
β Text encoder available. Difference by 0.001953125
xlYamersRealistic_v3
π΄ Text encoder unavailable. Same as SDXL 1.0 Base
xxMix9RealisticSDXL_Testv20
β Text encoder available. Difference by 0.001953125
zavyChromaXL_b2
π΄ Text encoder unavailable. Same as SDXL 1.0 Base