<h2 id="doll-style-bjd-photography-lora-or-anima-ver.">Doll Style / BJD Photography LoRA | Anima ver.</h2>这是一个基于 Anima base v1.0 训练的 LoRA 模型，专注于生成 BJD (Ball-jointed doll) 娃娃摄影风格的图像。This is a LoRA model trained on Anima base v1.0, specializing in generating images in a BJD (Ball-jointed doll) photography style.<hr /><h3 id="or-how-to-use">💡 如何使用 | How to use</h3><ul><li>无触发词，直接使用 | No trigger word required, use directly.</li><li>权重: <code>1.0</code> | Weight: <code>1.0</code></li></ul>1. ⚙️ 参数设置 | Settings (CFG, Steps)<ul><li><code>CFG</code> 和 <code>Steps</code> 等参数可以灵活调整，但我推荐从 CFG 4~5、Steps 30 开始尝试。具体设置请参考示例图片的元数据（Metadata），图像中包含了 ComfyUI 工作流信息。</li><li>Parameters such as <code>CFG</code> and <code>Steps</code> can vary, but I recommend starting with CFG 4~5 and 30 steps. For specific settings, please refer to the metadata of the sample images, which contain ComfyUI workflow information.</li></ul>2. ✨ 高清修复 | Hires Fix<ul><li>开启 Hires Fix后，可以更好还原 BJD 的皮肤、发丝纹理和眼部细节。</li><li>With Hires Fix enabled, it can better restore the skin texture, hair strand details, and eye details.</li></ul><hr />Important reminder: Do not use for commercial purposes or publish on other public platforms重要提示：请勿商用并发表到其他公开平台

BJD Doll Style | Anima ver.

Base: Anima base v1.0Training parameters:<pre><code>resolution: 1024
reg_data_dir: null
reg_caption: null
reg_weight: 1.0
shuffle_caption: true
keep_tokens: 0
flip_augment: true
tag_dropout: 0.0
prefer_json: true
cache_latents: true
lora_type: lora
lora_rank: 32
lora_alpha: 32.0
lokr_factor: 8
lora_dora: true
lora_rs: false
lora_dropout: 0.0
lora_rank_dropout: 0.0
lora_module_dropout: 0.0
epochs: 15
max_steps: 0
batch_size: 2
grad_accum: 1
learning_rate: 1.0
lr_scheduler: none
lr_scheduler_t0: 500
lr_scheduler_t_mult: 2.0
lr_scheduler_eta_min: 1.0e-06
optimizer_type: prodigy_plus_schedulefree
prodigy_d_coef: 1.0
prodigy_safeguard_warmup: true
ppsf_d_coef: 1.0
ppsf_prodigy_steps: 0
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
noise_offset: 0.0
pyramid_noise_iters: 0
pyramid_noise_discount: 0.35
timestep_sampling: logit_normal
timestep_shift: 3.0
loss_weighting: min_snr
min_snr_gamma: 5.0
weight_cap_ratio: 0.0
grad_clip_max_norm: 0.0
mixed_precision: bf16
grad_checkpoint: true
attention_backend: none
num_workers: 0</code></pre>

Files with SHA256: 0d7e39196e8652187a33c72ae52c4be39d5ddf7fb86235a6edcabd39692fa000