diff --git a/README.md b/README.md
index d9636719..331951ef 100644
--- a/README.md
+++ b/README.md
@@ -11,6 +11,10 @@ The command to install PyTorch is as follows:
 
 ### Recent Updates
 
+Sep 1, 2024:
+- `--timestamp_sampling` has `flux_shift` option. Thanks to sdbds!
+  - This is the same shift as FLUX.1 dev inference, adjusting the timestep sampling depending on the resolution. `--discrete_flow_shift` is ignored when `flux_shift` is specified. It is not verified which is better, `shift` or `flux_shift`.
+
 Aug 29, 2024: 
 Please update `safetensors` to `0.4.4` to fix the error when using `--resume`. `requirements.txt` is updated.
 
@@ -73,6 +77,7 @@ There are many unknown points in FLUX.1 training, so some settings can be specif
   - `uniform`: uniform random
   - `sigmoid`: sigmoid of random normal, same as x-flux, AI-toolkit etc.
   - `shift`: shifts the value of sigmoid of normal distribution random number
+  - `flux_shift`: shifts the value of sigmoid of normal distribution random number, depending on the resolution (same as FLUX.1 dev inference). `--discrete_flow_shift` is ignored when `flux_shift` is specified.
 - `--sigmoid_scale` is the scale factor for sigmoid timestep sampling (only used when timestep-sampling is "sigmoid"). The default is 1.0. Larger values will make the sampling more uniform.
   - This option is effective even when`--timestep_sampling shift` is specified.
   - Normally, leave it at 1.0. Larger values make the value before shift closer to a uniform distribution.
diff --git a/library/flux_train_utils.py b/library/flux_train_utils.py
index 735bcced..9dad4baa 100644
--- a/library/flux_train_utils.py
+++ b/library/flux_train_utils.py
@@ -371,7 +371,7 @@ def compute_loss_weighting_for_sd3(weighting_scheme: str, sigmas=None):
 def get_noisy_model_input_and_timesteps(
     args, noise_scheduler, latents, noise, device, dtype
 ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
-    bsz, _, H, W = latents.shape
+    bsz, _, h, w = latents.shape
     sigmas = None
 
     if args.timestep_sampling == "uniform" or args.timestep_sampling == "sigmoid":
@@ -399,7 +399,7 @@ def get_noisy_model_input_and_timesteps(
         logits_norm = torch.randn(bsz, device=device)
         logits_norm = logits_norm * args.sigmoid_scale  # larger scale for more uniform sampling
         timesteps = logits_norm.sigmoid()
-        mu=get_lin_function(y1=0.5, y2=1.15)((H//2) * (W//2))
+        mu = get_lin_function(y1=0.5, y2=1.15)((h // 2) * (w // 2))
         timesteps = time_shift(mu, 1.0, timesteps)
 
         t = timesteps.view(-1, 1, 1, 1)
@@ -583,8 +583,8 @@ def add_flux_train_arguments(parser: argparse.ArgumentParser):
         "--timestep_sampling",
         choices=["sigma", "uniform", "sigmoid", "shift", "flux_shift"],
         default="sigma",
-        help="Method to sample timesteps: sigma-based, uniform random, sigmoid of random normal and shift of sigmoid."
-        " / タイムステップをサンプリングする方法：sigma、random uniform、random normalのsigmoid、sigmoidのシフト。",
+        help="Method to sample timesteps: sigma-based, uniform random, sigmoid of random normal, shift of sigmoid and FLUX.1 shifting."
+        " / タイムステップをサンプリングする方法：sigma、random uniform、random normalのsigmoid、sigmoidのシフト、FLUX.1のシフト。",
     )
     parser.add_argument(
         "--sigmoid_scale",