mally-2000/saii-cldm-ldm-checkpoints

SAII-CLDM LDM Checkpoints

This repository hosts the raw CompVis latent-diffusion checkpoints for SAII-CLDM. For the Diffusers-format release with bundled inference code, see mally-2000/saii-cldm-synthetic.

Files

File	Description
stage1_vqgan.ckpt	Stage 1 VQGAN checkpoint used as the first-stage autoencoder.
stage2_ldm.ckpt	Stage 2 SAII-CLDM latent diffusion checkpoint.
stage1_vqgan_marmousi.yaml	Public Stage 1 VQGAN model/data config.
stage2_saii_cldm_marmousi.yaml	Public Stage 2 SAII-CLDM model/data config.

There are two public YAML files because there are two model checkpoints. The Lightning trainer/logger/callback config used for training is part of the code repository, not this model-weight repository.

Download

pip install huggingface_hub
huggingface-cli download \
  --repo-type model \
  --local-dir ./saii-cldm-ldm-checkpoints \
  mally-2000/saii-cldm-ldm-checkpoints

Or in Python:

from huggingface_hub import snapshot_download

snapshot_download(
    "mally-2000/saii-cldm-ldm-checkpoints",
    repo_type="model",
    local_dir="./saii-cldm-ldm-checkpoints",
)

Use With The Code Repository

Clone the SAII-CLDM code repository:

git clone https://github.com/Mally-cj/cldm-diffusers.git
cd cldm-diffusers

Set the required local paths in .env:

cp .env.example .env
# edit FIRST_STAGE_CKPT, MARMousi_NPZ, and OVERTHRUST_DATA_DIR as needed

If you downloaded this repository next to the code repository, copy the checkpoints and public configs into the code repository:

mkdir -p models configs
cp ../saii-cldm-ldm-checkpoints/stage1_vqgan.ckpt models/
cp ../saii-cldm-ldm-checkpoints/stage2_ldm.ckpt models/
cp ../saii-cldm-ldm-checkpoints/stage1_vqgan_marmousi.yaml configs/
cp ../saii-cldm-ldm-checkpoints/stage2_saii_cldm_marmousi.yaml configs/

Set the required local paths in .env:

FIRST_STAGE_CKPT=./models/stage1_vqgan.ckpt
# set MARMousi_NPZ and OVERTHRUST_DATA_DIR to your local data paths

Run CLDM inference on the Overthrust benchmark:

CUDA_VISIBLE_DEVICES=0 python eval_overthrust.py CLDM \
  --ckpt ./models/stage2_ldm.ckpt \
  --config ./configs/stage2_saii_cldm_marmousi.yaml \
  --output runs/eval_cldm \
  --device cuda \
  --steps 30

If GPU 0 is occupied or you hit OOM, switch to another GPU:

CUDA_VISIBLE_DEVICES=1 python eval_overthrust.py CLDM \
  --ckpt ./models/stage2_ldm.ckpt \
  --config ./configs/stage2_saii_cldm_marmousi.yaml \
  --output runs/eval_cldm \
  --device cuda \
  --steps 30

To train Stage 1 VQGAN from scratch:

CUDA_VISIBLE_DEVICES=0 python train_latent_diffusion.py -t \
  --base ./configs/stage1_vqgan_marmousi.yaml

To train Stage 2 SAII-CLDM from scratch, use the code repository's configs/training_lightning.yaml together with the Stage 2 model/data config:

CUDA_VISIBLE_DEVICES=0 python train_latent_diffusion.py -t \
  --base ./configs/stage2_saii_cldm_marmousi.yaml ./configs/training_lightning.yaml

To continue Stage 2 training from the released checkpoint, add --resume:

CUDA_VISIBLE_DEVICES=0 python train_latent_diffusion.py -t \
  --resume ./models/stage2_ldm.ckpt \
  --base ./configs/stage2_saii_cldm_marmousi.yaml ./configs/training_lightning.yaml

Paper

Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion Model. arXiv: 2506.13529