Tensor.Art
Erstellen

FF Safe AnimXL (Lora, Lycoris +dataset) - Safe AnimeXL-Lycoris V.3

FF Safe AnimXL (Lora, Lycoris +dataset)

LORA
Original

Aktualisiert:

Safe AnimXL - For Merge
Safe AnimXL - TX ENCODER
Safe AnimeXL-Lycoris V.3
Safe AnimXL (LyCORIS Mix)
Civitai Lora - Dataset
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art
FF Safe AnimXL (Lora, Lycoris +dataset) by FFusionAI on Tensor.Art

🌟 Trained specifically for style mixing on Safe For Work (SFW) dataset.

🔹 Text Encoder (strongly reliant on U-Net architecture):

🔹 Lora Model:

  • Trained using the CivitAI trainer.

  • Underwent training for 16 epochs.

  • Performance: Lora showcases stable diffusion in XL settings.

🔹 Lycoris Models:

  • Configured using this preset from LyCORIS, but with our custom tweaks.

  • Trained on 8xA6000 GPUs.

  • Underwent 20-40 epochs with a batch size of 20.

  • Module Type Breakdown:

    • LohaModule: 176

    • LoConModule: 150

    • FullModule: 26

    • LokrModule: 700

🏆 Comparison:

  • CivitAI's Lora stands out in our tests, but we've yet to explore its full potential in style mixing with other models.

Feedback, collaboration, and tests are welcome! 🤟 🥃

Versionsdetails

SDXL 1.0
<p>Mixed training experiment using | lokr lora loha</p><p>More balanced dims (lower size)</p><p>module type table: {'<strong>LohaModule</strong>': 176, '<strong>LoConModule</strong>': 150, '<strong>FullModule</strong>': 26, '<strong>LokrModule</strong>': 700}</p><pre><code> @unet_target_module = [ "Transformer2DModel", "ResnetBlock2D", "Downsample2D", "Upsample2D", ] unet_target_name = [ "conv_in", "conv_out", "time_embedding.linear_1", "time_embedding.linear_2", ] text_encoder_target_module = [ "CLIPAttention", "CLIPMLP", ] [module_algo_map] [module_algo_map.CrossAttention] # Attention Layer in UNet algo = "lokr" [module_algo_map.FeedForward] # MLP Layer in UNet algo = "lokr" [module_algo_map.ResnetBlock2D] # ResBlock in UNet algo = "lora" [module_algo_map.CLIPAttention] # Attention Layer in TE algo = "loha" [module_algo_map.CLIPMLP] # MLP Layer in TE algo = "lora" </code></pre>

Projektberechtigungen

    Berechtigungen verwenden

  • Verwenden Sie in TENSOR Online

  • Als ein Online-Trainings-Basismodell auf TENSOR

  • Verwenden ohne meine Berechnung

  • Teile Zusammenführungen dieses Modells

  • Verwende unterschiedliche Berechtigungen für Merges

    Kommerzielle Nutzung

  • Verkaufen Sie generierte Inhalte

  • Verwendung auf Generierungsdiensten

  • Verkaufen Sie dieses Modell oder führen Sie Merges durch

Verwandte Beiträge