Flat Color - Style
Trained on images without visible lineart, flat colors, and little to no indication of depth.
ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models and workflow/training information.
This is a small style LoRA I thought would be interesting to try with a v-pred model (noobai v-pred), for the reduced color bleeding and strong blacks in particular.
The effect is quite nice and easy to evaluate in training, so I've extended the dataset with videos in following versions for text-to-video models like Wan and Hunyuan, and it is what I am generally using to test LoRA training on new models now.
Recommended prompt structure:
Positive prompt:
flat color, no lineart, blending, negative space,
{{tags}}
masterpiece, best quality, very aesthetic, newestDescription
[WAN 2.2 TI2V 5B] LoRA
Trained with diffusion-pipe on Wan2.2-TI2V-5B
Experimental - first test for Wan 2.2 training
Image dataset only
Less effect at longer framerates
Text to Video previews generated with ComfyUI_examples/wan22/#text-to-video
Loading the LoRA with LoraLoaderModelOnly node
dataset.toml
# Resolution settings.
resolutions = [1024]
# 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/training_data/images'
num_repeats = 5
resolutions = [1024]config.toml
# Dataset config file.
output_dir = '/mnt/d/wan/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
# blocks_to_swap=32
# 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 = 5
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 = 'wan'
ckpt_path = '../Wan2.2-TI2V-5B'
dtype = 'bfloat16'
# You can use fp8 for the transformer when training LoRA.
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