animov-512x / config.yaml
bruefire
fixed workflow.md a bit.
99b4771
pretrained_model_path: ./outputs/train_2023-05-02T00-50-05/checkpoint-15000/
output_dir: ./outputs/
train_data:
width: 512
height: 512
use_bucketing: true
sample_start_idx: 1
fps: 24
frame_step: 5
n_sample_frames: 45
single_video_path: ''
single_video_prompt: ''
fallback_prompt: ''
path: E:/userdata/Pictures/ai_trainning/t2v-v2/gif/vid/old/
json_path: ./json/anime-v2.json
image_dir: E:/userdata/Pictures/ai_trainning/t2v-v2/img/
single_img_prompt: ''
validation_data:
prompt: ''
sample_preview: true
num_frames: 16
width: 512
height: 512
num_inference_steps: 25
guidance_scale: 9
dataset_types:
- json
- image
validation_steps: 100
extra_unet_params: null
extra_text_encoder_params: null
train_batch_size: 1
max_train_steps: 10000
learning_rate: 5.0e-06
scale_lr: false
lr_scheduler: constant
lr_warmup_steps: 0
adam_beta1: 0.9
adam_beta2: 0.999
adam_weight_decay: 0.01
adam_epsilon: 1.0e-08
max_grad_norm: 1.0
gradient_accumulation_steps: 1
checkpointing_steps: 2500
resume_from_checkpoint: null
mixed_precision: fp16
use_8bit_adam: false
enable_xformers_memory_efficient_attention: false
enable_torch_2_attn: true
seed: 64
extend_dataset: false
cached_latent_dir: null
use_unet_lora: true
unet_lora_modules:
- ResnetBlock2D
text_encoder_lora_modules:
- CLIPEncoderLayer
lora_rank: 25
lora_path: ''
kwargs: {}
cache_latents: true
gradient_checkpointing: true
offset_noise_strength: 0.1
text_encoder_gradient_checkpointing: false
train_text_encoder: false
trainable_modules:
- attn1
- attn2
- temp_conv
trainable_text_modules:
- all
use_offset_noise: false
use_text_lora: true