Update README.md

README.md

@@ -19,6 +19,8 @@ Our generative model has `Next-DiT` as the backbone, the text encoder is the `Ge
 
 ## 📰 News
 
+- [2024-5-28] 🚀🚀🚀 We updated the `Lumina-Next-T2I` model for supporting 2K Resolution image generation.
+
 - [2024-5-16] ❗❗❗ We have converted the `.pth` weights to `.safetensors` weights. Please pull the latest code to use `demo.py` for inference.
 
 - [2024-5-12] 🚀🚀🚀 We release the next version of `Lumina-T2I`, called `Lumina-Next-T2I` for faster and lower memory usage image generation model.
@@ -164,13 +166,6 @@ Update your own personal inference settings to generate different styles of imag
     reverse: false                  # option: true or false
     likelihood: false               # option: true or false
 
-  sde:
-    sampling_method: "Euler"        # option: ["Euler", "Heun"]
-    diffusion_form: "sigma"         # option: ["constant", "SBDM", "sigma", "linear", "decreasing", "increasing-decreasing"]
-    diffusion_norm: 1.0             # range: 0-1
-    last_step: Mean                 # option: [None, "Mean", "Tweedie", "Euler"]
-    last_step_size: 0.04
-
   infer:
       resolution: "1024x1024"     # option: ["1024x1024", "512x2048", "2048x512", "(Extrapolation) 1664x1664", "(Extrapolation) 1024x2048", "(Extrapolation) 2048x1024"]
       num_sampling_steps: 60      # range: 1-1000
@@ -197,12 +192,6 @@ Update your own personal inference settings to generate different styles of imag
   - `rtol`: Relative tolerance for the ODE solver. (option: ["velocity", "score", "noise"])
   - `reverse`: run the ODE solver in reverse. (option: [None, "velocity", "likelihood"])
   - `likelihood`: Enable calculation of likelihood during the ODE solving process.
-- sde
-  - `sampling-method`: the numerical method used for sampling the stochastic differential equation: 'Euler' for simplicity or 'Heun' for improved accuracy.
-  - `diffusion-form`: form of diffusion coefficient in the SDE
-  - `diffusion-norm`: Normalizes the diffusion coefficient, affecting the scale of the stochastic component.
-  - `last-step`: form of last step taken in the SDE
-  - `last-step-size`: size of the last step taken
 - infer
   - `resolution`: generated image resolution.
   - `num_sampling_steps`: sampling step for generating image.