Update README.md

README.md

@@ -34,25 +34,110 @@ MajicFlus 模型在发布的同时，多位社区成员基于模型制作的 LoR
 - 由于该模型是个微调融合模型，对社区大部分的lora都是不完美兼容的，需要降低权重至0.5以下。推荐使用带有majicFlus标志的矩阵模型，搜索关键字majic并筛选f1模型就可以看到全部，现在已有超过50款风格各异的优质模型。
 
 ## 参数推荐 Parameter
-Steps: 20~30
+- Steps: 20~30
-Distilled CFG Scale: 3.5
+- Distilled CFG Scale: 3.5
-CFG : 1
+- CFG : 1
-Diffusion in Low Bits: float8-e4m3fn
+- Diffusion in Low Bits: float8-e4m3fn
-Sampling: Euler + simple/beta (for general)，DPM2M + SGM uniform (for skin texture)，DEIS + DDIM uniform (for casual realistic look)
+- Sampling: Euler + simple/beta (for general)，DPM2M + SGM uniform (for skin texture)，DEIS + DDIM uniform (for casual realistic look)
-Vae: flux vae
+- Vae: flux vae
-Clip: clip_l.safetensors and t5xxl_fp8_e4m3fn.safetensors
+- Clip: clip_l.safetensors and t5xxl_fp8_e4m3fn.safetensors
 
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+## 生图
 
-SDK下载
+本模型可通过[AIGC专区生图](https://www.modelscope.cn/aigc/imageGeneration?tab=advanced&versionId=14497&modelType=Checkpoint&sdVersion=FLUX_1&modelUrl=modelscope%3A%2F%2FMAILAND%2Fmajicflus_v1%3Frevision%3Dv1.0)直接在线使用。也通过ModelScope API-Inference使用（见本页面右侧）。
-```bash
+
-#安装ModelScope
+如果要下载模型到本地进行推理生图，**建议使用DiffSynth-Studio** 提供的生图pipeline。
-pip install modelscope
+
+### 安装DiffSynth
 ```
+pip install diffsynth -U
+```
+
+### 推理生图
+
+#### 量化推理（需要至少 14G 显存，且需较大的内存）
+推荐方式，能在较小显存下，实现无损生图。
+
 ```python
-#SDK模型下载
+import torch
 from modelscope import snapshot_download
-model_dir = snapshot_download('merjic/majicflus_v1')
+from diffsynth import ModelManager, FluxImagePipeline
+
+# 下载模型
+snapshot_download(
+    model_id="MAILAND/majicflus_v1",
+    allow_file_pattern="majicflus_v134.safetensors",
+    cache_dir="models"
+)
+snapshot_download(
+    model_id="black-forest-labs/FLUX.1-dev",
+    allow_file_pattern=["ae.safetensors", "text_encoder/model.safetensors", "text_encoder_2/*"],
+    cache_dir="models"
+)
+
+# 设置推理计算精度为 bfloat16
+model_manager = ModelManager(torch_dtype=torch.bfloat16)
+# 以 float8 精度加载 DiT 部分
+model_manager.load_models(
+    ["models/MAILAND/majicflus_v1/majicflus_v134.safetensors"],
+    torch_dtype=torch.float8_e4m3fn,
+    device="cpu"
+)
+# 以 bfloat16 精度加载两个 Text Encoder 和 VAE
+model_manager.load_models(
+    [
+        "models/black-forest-labs/FLUX.1-dev/text_encoder/model.safetensors",
+        "models/black-forest-labs/FLUX.1-dev/text_encoder_2",
+        "models/black-forest-labs/FLUX.1-dev/ae.safetensors",
+    ],
+    torch_dtype=torch.bfloat16,
+    device="cpu"
+)
+# 开启量化与显存管理
+pipe = FluxImagePipeline.from_model_manager(model_manager, device="cuda")
+pipe.enable_cpu_offload()
+pipe.dit.quantize()
+
+# 生图！
+image = pipe(prompt="a beautiful girl", seed=0)
+image.save("image.jpg")
+```
+
+#### 原生精度推理（需要至少 40G 显存）
+
+```python
+import torch
+from modelscope import snapshot_download
+from diffsynth import ModelManager, FluxImagePipeline
+
+# 下载模型
+snapshot_download(
+    model_id="MAILAND/majicflus_v1",
+    allow_file_pattern="majicflus_v134.safetensors",
+    cache_dir="models"
+)
+snapshot_download(
+    model_id="black-forest-labs/FLUX.1-dev",
+    allow_file_pattern=["ae.safetensors", "text_encoder/model.safetensors", "text_encoder_2/*"],
+    cache_dir="models"
+)
+
+# 加载模型
+model_manager = ModelManager(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    file_path_list=[
+        "models/black-forest-labs/FLUX.1-dev/text_encoder/model.safetensors",
+        "models/black-forest-labs/FLUX.1-dev/text_encoder_2",
+        "models/black-forest-labs/FLUX.1-dev/ae.safetensors",
+        "models/MAILAND/majicflus_v1/majicflus_v134.safetensors",
+    ]
+)
+pipe = FluxImagePipeline.from_model_manager(model_manager, device="cuda")
+
+# 生图！
+image = pipe(prompt="a beautiful girl", seed=0)
+image.save("image.jpg")
 ```
 Git下载
 ```