From d24c5c29fa079c56bcfe5325e85f9bde5e34a626 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jukka=20Sepp=C3=A4nen?=
<40791699+kijai@users.noreply.github.com>
Date: Sun, 16 Jun 2024 18:34:47 +0300
Subject: [PATCH] Update README.md
---
README.md | 158 ++----------------------------------------------------
1 file changed, 5 insertions(+), 153 deletions(-)
diff --git a/README.md b/README.md
index 3e18571..a4e73e6 100644
--- a/README.md
+++ b/README.md
@@ -1,157 +1,9 @@
-
- 
-
-
+# WORK IN PROGRESS
-# Lumina-Next-T2I-Mini
-
-`Lumina-Next-T2I-Mini` is a simplified version of `Lumina-Next-T2I`, with
-1. trimmed `transport` module; and
-2. removed model-parallel stuff (which exists but makes no effect in the `Lumina-Next-T2I` project)
-
-Though simplified, this directory retains **all** the functionalities that were *actually used* by us during the training and inference of Lumina-Next-T2I
-
-## 🎮 Model Zoo
-
-More checkpoints of our model will be released soon~
-
-| Resolution | Next-DiT Parameter| Text Encoder | Prediction | Download URL |
-| ---------- | ----------------------- | ------------ | -----------|-------------- |
-| 1024 | 2B | [Gemma-2B](https://huggingface.co/google/gemma-2b) | Rectified Flow | [hugging face](https://huggingface.co/Alpha-VLLM/Lumina-Next-T2I) |
-
-## Installation
-
-Before installation, ensure that you have a working ``nvcc``
-
-```bash
-# The command should work and show the same version number as in our case. (12.1 in our case).
-nvcc --version
-```
-
-On some outdated distros (e.g., CentOS 7), you may also want to check that a late enough version of
-``gcc`` is available
-
-```bash
-# The command should work and show a version of at least 6.0.
-# If not, consult distro-specific tutorials to obtain a newer version or build manually.
-gcc --version
-```
-
-Downloading Lumina-T2X repo from github:
-
-```bash
-git clone https://github.com/Alpha-VLLM/Lumina-T2X
-```
-
-### 1. Create a conda environment and install PyTorch
-
-Note: You may want to adjust the CUDA version [according to your driver version](https://docs.nvidia.com/deploy/cuda-compatibility/#default-to-minor-version).
-
- ```bash
- conda create -n Lumina_T2X -y
- conda activate Lumina_T2X
- conda install python=3.11 pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia -y
- ```
-
-### 2. Install dependencies
-
- ```bash
- pip install diffusers accelerate tensorboard transformers gradio torchdiffeq click
- ```
-
- or you can use
-
- ```bash
- cd lumina_next_t2i
- pip install -r requirements.txt
- ```
-
-### 3. Install ``flash-attn``
-
- ```bash
- pip install flash-attn --no-build-isolation
- ```
-
-### 4. Install [nvidia apex](https://github.com/nvidia/apex) (optional)
-
->[!Warning]
-> While Apex can improve efficiency, it is *not* a must to make Lumina-T2X work.
->
-> Note that Lumina-T2X works smoothly with either:
-> + Apex not installed at all; OR
-> + Apex successfully installed with CUDA and C++ extensions.
->
-> However, it will fail when:
-> + A Python-only build of Apex is installed.
->
-> If the error `No module named 'fused_layer_norm_cuda'` appears, it typically means you are using a Python-only build of Apex. To resolve this, please run `pip uninstall apex`, and Lumina-T2X should then function correctly.
-
-You can clone the repo and install following the official guidelines (note that we expect a full
-build, i.e., with CUDA and C++ extensions)
-
-```bash
-pip install ninja
-git clone https://github.com/NVIDIA/apex
-cd apex
-# if pip >= 23.1 (ref: https://pip.pypa.io/en/stable/news/#v23-1) which supports multiple `--config-settings` with the same key...
-pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
-# otherwise
-pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --global-option="--cpp_ext" --global-option="--cuda_ext" ./
-```
-
-## Inference
-
-### Prepare Checkpoints
-
-#### 1. Download pretrained checkpoints
-
-⭐⭐ (Recommended) you can use huggingface_cli downloading our model:
-
-```bash
-huggingface-cli download --resume-download Alpha-VLLM/Lumina-Next-T2I --local-dir /path/to/ckpt
-```
-
-or using git for cloning the model you want to use:
-
-```bash
-git clone https://huggingface.co/Alpha-VLLM/Lumina-Next-T2I
-```
+## Currently requires `flash_attn` !
-#### 2. Use checkpoints trained by yourself
+
-If you are loading your own trained model, please convert `*.pth` files to `.safetensors` first for security reasons before loading. Assuming your trained model path is `/path/to/your/own/model.pth` and your save directory is `/path/to/new/model`.
-
-```bash
-lumina_next convert "/path/to/your/own/model.pth" "/path/to/new/directory/" # convert to `.safetensors`
-```
-
-Explanation of the `lumina_next convert` command:
-```bash
-# means your trained model path.
-# means the directory where you want to save the model.
-lumina_next convert
-
-# example 1:
-lumina_next convert "/path/to/your/own/model.pth" "/path/to/new/directory/" # convert to `.safetensors`
-
-# example 2:
-lumina_next convert "/path/to/your/own/model.safetensors" "/path/to/new/directory/" # convert to `.pth`
-```
-
-### Web Demo
-
-To host a local gradio demo for interactive inference, run the following command:
-
-```bash
-# `/path/to/ckpt` should be a directory containing `consolidated*.pth` and `model_args.pth`
-
-# default
-python -u demo.py --ckpt "/path/to/ckpt"
-
-# the demo by default uses bf16 precision. to switch to fp32:
-python -u demo.py --ckpt "/path/to/ckpt" --precision fp32
-
-# use ema model
-python -u demo.py --ckpt "/path/to/ckpt" --ema
-```
+Original repo:
+https://github.com/Alpha-VLLM/Lumina-T2X