mirror of
https://github.com/huggingface/diffusers.git
synced 2026-10-27 21:33:02 +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>
16 lines
219 B
Plaintext
16 lines
219 B
Plaintext
--extra-index-url https://download.pytorch.org/whl/cu130
|
|
torch
|
|
torchvision
|
|
accelerate>=0.31.0
|
|
huggingface_hub
|
|
imageio
|
|
imageio-ffmpeg
|
|
transformers>=4.41.2
|
|
peft>=0.11.1
|
|
datasets
|
|
numpy
|
|
tqdm
|
|
sentencepiece
|
|
tensorboard
|
|
wandb
|