├── results │├── models │├── ffhq_10m.pt # FFHQ for training │├── 256x256_diffusion_uncond.pt # ImageNet for training │└── official_ckpt # For Evaluation │ ├── ffhq │ │ ├── gaussian_ema.pt │ │ ├── sr_averagepooling_ema.pt │ │ ├── ... ...
From thelink, download the FFHQ checkpointffhq_10m.pt, rename todiffusion_ffhq_10m.pt, and paste it to../model_zoo. To run guidance based onAnalyticposterior covariance, download the precomputed Monte Carlo estimation from thelink, and paste it to./runs. ...
2. 通用框架 2.1 去噪扩散概率模型（DDPMs）2.2 噪声条件评分网络（NCSNs）2.3随机微分方程（SDE）...
Do not forget to rename "ffhq_10m" to "diffusion_ffhq_m" for code consistency.Inference Codepython main_ddpir_sisr.py # SR python main_ddpir_deblur.py # deblur python main_ddpir_inpainting.py # inpaintingAlternatively:python main_ddpir.py --opt configs/sisr.yaml # SR python main_ddpir...
From the [link](https://drive.google.com/drive/folders/1jElnRoFv7b31fG0v6pTSQkelbSX3xGZh?usp=sharing), download the FFHQ checkpoint "ffhq_10m.pt", rename to "diffusion_ffhq_10m.pt", and paste it to "../model_zoo". From the [link](https://drive.google.com/drive/folders/...
From the link, download the checkpoint "ffhq_10m.pt" and paste it to ./models/;From the link, download the checkpoint "lsun_bedroom.pt" and paste it to ./models/.mkdir models mv {DOWNLOAD_DIR}/celebahq_p2.pt ./models/ mv {DOWNLOAD_DIR}/ffqh_10m.pt ./models/ mv {DOWNLOAD_DIR}...
Download the public available FFHQ checkpoint (ffhq_10m.pt) here. # in DAPS folder mkdir checkpoint mv {DOWNLOAD_DIR}/ffqh_10m.pt checkpoint/ffhq256.pt (Optional) For nonlinear deblur task, we need the pretrained model from bkse at here: # in DAPS folder mv {DOWNLOAD_DIR}/GOPRO_wV...
noise_schedule linear --num_channels 128 --num_head_channels 64 --num_res_blocks 1 --resblock_updown True --use_fp16 False --use_scale_shift_norm True --timestep_respacing 100 --model_path models/ffhq_10m.pt --base_samples ref_imgs/face --down_N 32 --range_t 20 --save_dir...
From the link, download the FFHQ checkpoint ffhq_10m.pt, rename to diffusion_ffhq_10m.pt, and paste it to ../model_zoo. To run guidance based on Analytic posterior covariance, download the precomputed Monte Carlo estimation from the link, and paste it to ./runs. To run guidance based on...
noise_schedule linear --num_channels 128 --num_head_channels 64 --num_res_blocks 1 --resblock_updown True --use_fp16 False --use_scale_shift_norm True --timestep_respacing 100 --model_path models/ffhq_10m.pt --base_samples ref_imgs/face --down_N 32 --range_t 20 --save_dir...