<h2 id="anima-version">Anima Version</h2>This is an experimental LoRA version trained on Anima Preview.Anima is a new DiT model focused on anime concepts. You can find it on Hugging Face at <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima">circlestone-labs/Anima · Hugging Face</a> Trigger word<pre><code>@4x0style</code></pre>Recommended strength is 1.0 Recommendation to Anima Lora Trainer I am working on <span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:14px">/ᐠ ̷ ̷𝅒 ̷‸ ̷𝅒 ̷ ᐟ\ﾉ<a target="_blank" rel="ugc" href="https://github.com/WalkingMeatAxolotl/AnimaLoraStudio">https://github.com/WalkingMeatAxolotl/AnimaLoraStudio</a> <pre><code>transformer_path: ~
vae_path: ~
text_encoder_path: ~
t5_tokenizer_path: ~
data_dir: ~
resolution:
- 1024
aspect_ratio_limit: 2.0
reg_data_dir: ~
reg_caption: null
reg_weight: 0.5
shuffle_caption: true
keep_tokens: 1
flip_augment: true
tag_dropout: 0.0
prefer_json: true
caption_comfy_encoding: true
cache_latents: true
vae_cache_batch_size: 0
navit_packing: false
cache_encode_tiled: false
lora_type: lokr
lora_rank: 32
lora_alpha: 32.0
lokr_factor: 4
lora_dora: false
lora_rs: false
lora_dropout: 0.0
lora_rank_dropout: 0.0
lora_module_dropout: 0.05
lora_reg_dims: null
epochs: 40
max_steps: 0
batch_size: 2
grad_checkpoint: true
grad_accum: 2
learning_rate: 1.0
lr_scheduler: none
optimizer_type: prodigy_plus_schedulefree
ppsf_d_coef: 2.0
ppsf_prodigy_steps: 1800
ppsf_beta1: 0.9
ppsf_beta2: 0.99
ppsf_split_groups: true
ppsf_split_groups_mean: false
ppsf_use_speed: false
ppsf_fused_back_pass: false
ppsf_use_stableadamw: true
weight_decay: 0.0
kv_trim: false
vae_tiling: auto
noise_enhancement_type: none
timestep_sampling: uniform
timestep_schedule_shift: 0.7
timestep_shift_resolution_aware: false
infonoise_enabled: false
loss_type: mse
loss_weighting: none
leap_enabled: true
leap_ratio: 0.3
leap_variant: original
leap_nested_grad_coe: 0.3
leap_min_gap: 0.1
leap_traj_sim_weighting: true
leap_traj_sim_min: 0.1
sra_enabled: false
grad_clip_max_norm: 0.0
mixed_precision: bf16
attention_backend: flash_attn
num_workers: 0
output_dir: ~
output_name: ~
save_every_epochs: 2
save_every_steps: 0
save_state_every_epochs: 1000
save_state_every_steps: 0
seed: 42
resume_lora: null
resume_state: null</code></pre>------------------------------------------------------------------------------------------<h2 id="noob-version"> Noob Version</h2>Trained on NoobAI V-Prediction. Trigger word<pre><code>ny4hu</code></pre>Recommended strength is 1.0 on WaiNoob

Files with SHA256: d71f43ce78a0edc04308ee51cf5d20cd13d4ea5bd78884f437619b502552232f