mirror of
https://github.com/huggingface/diffusers.git
synced 2026-10-24 20:59:27 +03:00
4ca863323d
* support lora for cosmos 2.5
* Fix inconsistencies with cosmos official repo in VAE encoding, text encoder attention implementation, and timestep scaling
* Support f_min and f_max in linear_scheduler warmup
* Add requirements and dataset preprocessing scripts to run examples
* Add LoRA training scripts
* Add LoRA eval scripts
* add assets for blogpost
* Fix(scheduler): device mismatch from upstream b114620 - move rk and b to device before torch.stack
* Always upcast to fp32
* Directly inhrit from LoraBaseMixin
* remove flash-attn2
* Use _keep_in_fp32_modules instead of autocast
* remove the get_latent_shape_cthw method and fix style
* simplifiy the eval script to make it more user-friendly
* overwrite scheduling_unipc_multistep.py with main's version
* remove network_alphas and add # Copied from
* remove figures and assets
* revert scheduler
* revert fp32 upcast and support bs > 1
---------
Co-authored-by: Ting-Yun Chang <tingyunc@nvidia.com>
19 lines
640 B
Bash
19 lines
640 B
Bash
export MODEL_NAME="nvidia/Cosmos-Predict2.5-2B"
|
|
export DATA_DIR="gr1_dataset/train"
|
|
export OUT_DIR=YOUR_OUTPUT_DIR
|
|
lora_rank=32
|
|
revision="diffusers/base/post-trained"
|
|
|
|
export TOKENIZERS_PARALLELISM=false
|
|
accelerate launch --mixed_precision="bf16" train_cosmos_predict25_lora.py \
|
|
--pretrained_model_name_or_path=$MODEL_NAME --revision $revision \
|
|
--train_data_dir=$DATA_DIR \
|
|
--train_batch_size=1 \
|
|
--num_train_epochs=500 --checkpointing_epochs=100 \
|
|
--seed=0 \
|
|
--output_dir=$OUT_DIR \
|
|
--report_to=wandb \
|
|
--height 432 --width 768 \
|
|
--allow_tf32 --gradient_checkpointing \
|
|
--lora_rank $lora_rank --lora_alpha $lora_rank
|