Trained with diffusion-pipe on HiDream-I1-Full
- 1480 steps on a 4090 over ~7hrs
Previews generated with ComfyUI_examples/hidream/#hidream-dev-workflow
- Loading the LoRA with LoraLoaderModelOnly node and using the HiDream DEV fp8 model: hidream_i1_dev_fp8.safetensors

config.toml

# Dataset config file.
output_dir = '/mnt/d/hidream/training_output'
dataset = 'dataset-hidream.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 = 20

# 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 = 10
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_beginning'

[model]
type = 'hidream'
diffusers_path = '../hidream-full'
llama3_path = '../llama-3.1'
llama3_4bit = true
dtype = 'bfloat16'
transformer_dtype = 'nf4'
max_llama3_sequence_length = 256
flux_shift = true

[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

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/huanvideo/training_data/images'
num_repeats = 5
resolutions = [1024]

0 comment