CivArchive
    Preview 3147774
    Preview 3146847
    Preview 3146838
    Preview 3146845
    Preview 3146839
    Preview 3146842
    Preview 3146841
    Preview 3146840
    Preview 3146849
    Preview 3146850
    Preview 3146855
    Preview 3146856
    Preview 3146857
    Preview 3146859
    Preview 3146862
    Preview 3146860
    Preview 3146858
    Preview 3146861

    🚗 We Are Electric ⚡

    Harnessing the energy of the future, we present a series of LoRAs dedicated to the world of electric cars, EV charging concepts, and more.

    Experiment Setup:

    • Hardware: 6x A6000 GPUs

    • Special Mention: Lora 5 was trained using the CivitAI trainer.

    XYZ @ https://civarchive.com/articles/2719/we-are-electric-xyz


    Loras:

    1. Lora FA

      • Module: networks.lora_fa

      • Dim: 64

      • Alpha: 64.0

    2. Lycoris - preset FULL

      • Module: lycoris.kohya

      • Resolution: 1024x1024

      • Preset: full

      • Algo: lora

      • Dropout: 0.0

    3. Lycroris LoKR preset FULL with SDXL v-prediction

      • Preset: full

      • Algo: lokr

      • Factor: 8

      • Dim: 100,000,000

      • Alpha: 0.69

    4. LoRA - High Alpha Experiment (1.7GB oversized lora)

      • Module: networks.lora

      • Dim: 256

      • Alpha: 512.0

    5. CivitAI Lora

      • Resolution: 1024x1024

      • Architecture: stable-diffusion-xl-v1-base/lora

      • Learning Rate: 0.0005

      • UNet LR: 0.0005

      • TE LR: 5e-05

      • Network Dim/Rank: 32.0 Alpha: 1.0

      • Optimizer: bitsandbytes.optim.adamw.AdamW8bit(weight_decay=0.1)

      • Epoch: 15

      • Batches per epoch: 455

      • Gradient accumulation steps: 1

        Train images: 1820

      • Regularization images: 0

        Multires noise iterations: 6.0

      • Multires noise discount: 0.3

      • Min SNR gamma: 5.0

        UNet weight average magnitude: 4.496516309802129

        UNet weight average strength: 0.016011949140159916

        Text Encoder (1) weight average magnitude: 1.8189308640704058

        Text Encoder (1) weight average strength: 0.009030077111409775

        Text Encoder (2) weight average magnitude: 1.835224805119421

        Text Encoder (2) weight average strength: 0.007039581994775502

    6. FFusion LoRA:

      • Description: Merged and scaled using dynamic weights from LoRAS 1-5.

    Tags:

    futuristic product car shot, charging through city, futuristic car concept, futuristic cars, hydrogen fuel cell vehicle, render of futuristic supercar, by thomas häfner, tesla car, automotive, trending on vehicle design ... and 1988 more!
    

    🌐 FFusion.ai Contact Information

    Proudly maintained by Source Code Bulgaria Ltd & Black Swan Technologies.

    • 📧 For collaborations, inquiries, or support: [email protected]

    • 🌍 Locations: Sofia | Istanbul | London

    Connect with Us:

    Our Websites:

    Description

    Dynamic resize with sv_cumulative: 1.0 from 384

    FAQ

    Comments (5)

    denrakeiwOct 24, 2023· 1 reaction
    CivitAI

    It's interesting to see how the Civitai trainer compares to the other LoRa/Lycoris. I'm curious about an X/Y comparison.

    idle
    Author
    Oct 24, 2023· 1 reaction

    give me 30 min bud. uploading them all

    CIvitAI actually on a smaller dataset only 910 did really impressive .
    the others are trained on 2-3k datasets.
    also the final version is interesting by merging them all and scale the weights to 64.
    will do XYZ after uploads for sure 🤟 🥃

    idle
    Author
    Oct 24, 2023
    Dr_DreamOct 24, 2023· 2 reactions
    CivitAI

    nope, only a V12 can give me erections nowadays

    idle
    Author
    Oct 24, 2023
    CivitAI
    LORA
    SDXL 1.0
    by idle

    Details

    Downloads
    218
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/24/2023
    Updated
    5/13/2026
    Deleted
    -

    Files

    FFusion-We-Are-Electric.64LORA.safetensors

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.