Downloads · 30 days
0
Yuanzhi/SlimFlow
SlimFlow is a machine learning model from Yuanzhi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Downloads · 30 days
0
Access
Public
Updated Dec 21, 2025
Repo size
4.4 GB
Likes
0
Public
Click a slice to open those files.
.pth4.4 GB · 99%
From the Hugging Face model README
cd SlimFlow
huggingface-cli download Yuanzhi/SlimFlow --local-dir ckpts
########################## CIFAR-10 ##########################
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/CIFAR_2_rectified_flow_100000edm_flip_warmup_300000_28m.pth" \
--config.eval.batch_size 64 \
--config.model.nf 128 --config.model.num_res_blocks 2 --config.data.image_size 32 --config.model.ch_mult '(1, 2, 2)'
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/CIFAR_2_rectified_flow_100000edm_flip_warmup_300000_15m.pth" \
--config.eval.batch_size 64 \
--config.model.nf 96 --config.model.num_res_blocks 2 --config.data.image_size 32 --config.model.ch_mult '(1, 2, 2)'
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/CIFAR_2_rectified_flow_100000edm_flip_warmup_300000_7m.pth" \
--config.eval.batch_size 64 \
--config.model.nf 64 --config.model.num_res_blocks 2 --config.data.image_size 32 --config.model.ch_mult '(1, 2, 2)'
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/CIFAR_2_rectified_flow_100000edm_flip_warmup_300000_3m.pth" \
--config.eval.batch_size 64 \
--config.model.nf 64 --config.model.num_res_blocks 1 --config.data.image_size 32 --config.model.ch_mult '(1, 1, 2)'
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/CIFAR_distill_2_rectified_flow_500000edm_lpips_use_teacher_15m.pth" \
--config.eval.batch_size 64 \
--config.model.nf 96 --config.model.num_res_blocks 2 --config.data.image_size 32 --config.model.ch_mult '(1, 2, 2)'
```bash
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/CIFAR_distill_2_rectified_flow_500000edm_lpips_use_teacher_7m.pth" \
--config.eval.batch_size 64 \
--config.model.nf 64 --config.model.num_res_blocks 2 --config.data.image_size 32 --config.model.ch_mult '(1, 2, 2)'
########################## ImageNet 64 ##########################
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/ImageNet_2_rectified_flow_400000edm_flip_warmup_300000_44m.pth" \
--config.eval.batch_size 64 \
--config.model.name DhariwalUNet --config.model.nf 128 --config.model.num_res_blocks 2 --config.model.ch_mult '(1, 2, 2, 2)' --config.data.num_classes 1000 --config.data.image_size 64 --config.model.attn_resolutions '32, 16'
python ./image_sampling.py \
--config ./configs/rectified_flow/cifar10_rf_gaussian.py \
--sampling_dir "./ckpts/ImageNet_distill_2_rectified_flow_500000edm_lpips_use_teacher_44m.pth" \
--config.eval.batch_size 64 \
--config.model.name DhariwalUNet --config.model.nf 128 --config.model.num_res_blocks 2 --config.model.ch_mult '(1, 2, 2, 2)' --config.data.num_classes 1000 --config.data.image_size 64 --config.model.attn_resolutions '32, 16'