《葬送的芙莉莲》芙莉莲混元视频LoRA

检查相应基础模型的版本

该 LoRA 旨在以高质量美学插画风格生成 Frieren 角色的图像。

关于此版本

使用https://github.com/tdrussell/diffusion-pipe进行训练

训练数据是以下内容的组合：

• 此模型卡使用的其他版本的图像
• 从多个视频中提取关键帧的图像
• 短视频片段~每段 40 帧

训练配置：

数据集.toml

# Aspect ratio bucketing settings
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7

[[directory]] # IMAGES
# Path to the directory containing images and their corresponding caption files.
path = '/mnt/d/huanvideo/training_data/images'
num_repeats = 5
resolutions = [1024]
frame_buckets = [1] # Use 1 frame for images.


[[directory]] # VIDEOS
# Path to the directory containing videos and their corresponding caption files.
path = '/mnt/d/huanvideo/training_data/videos'
num_repeats = 5
resolutions = [256] # Set video resolution to 256 (e.g., 244p).
frame_buckets = [33, 49, 81] # Define frame buckets for videos.

配置.toml

# Dataset config file.
output_dir = '/mnt/d/huanvideo/training_output'
dataset = 'dataset.toml'

# Training settings
epochs = 50
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 4
gradient_clipping = 1.0
warmup_steps = 100

# eval settings
eval_every_n_epochs = 5
eval_before_first_step = true
eval_micro_batch_size_per_gpu = 1
eval_gradient_accumulation_steps = 1

# misc settings
save_every_n_epochs = 15
checkpoint_every_n_minutes = 30
activation_checkpointing = true
partition_method = 'parameters'
save_dtype = 'bfloat16'
caching_batch_size = 1
steps_per_print = 1
video_clip_mode = 'single_middle'

[model]
type = 'hunyuan-video'

transformer_path = '/mnt/d/huanvideo/models/diffusion_models/hunyuan_video_720_cfgdistill_fp8_e4m3fn.safetensors'
vae_path = '/mnt/d/huanvideo/models/vae/hunyuan_video_vae_bf16.safetensors'
llm_path = '/mnt/d/huanvideo/models/llm'
clip_path = '/mnt/d/huanvideo/models/clip'

dtype = 'bfloat16'
transformer_dtype = 'float8'
timestep_sample_method = 'logit_normal'

[adapter]
type = 'lora'
rank = 32
dtype = 'bfloat16'

[optimizer]
type = 'adamw_optimi'
lr = 5e-5
betas = [0.9, 0.99]
weight_decay = 0.02
eps = 1e-8

触发词：	frieren elf white hair twintails pointy ears green eyes
使用提示：	Strength: 1

作品参照

frieren, pointy ears, (green eyes), elf, twintails, white hair,
flat color, no lineart, blending, negative space, artist:[john kafka|ponsuke kaikai|hara id 21|yoneyama mai|fuzichoco],
nude, convenient censoring, upper body, hand on own chest, foreshortening, blue flower, high quality cinematic video of an elf laying in a field of glowing blue flowers under the starry night sky. The Camera is zooming in, she is viewed from the side laying on her back. There are moon rays and shadows. This is an upper body shot. The animation is smooth and fluid.