Update README.md

README.md

@@ -106,3 +106,57 @@ images = pipe(
 )[0][0]
 ```
 
+# Load Pipeline ( Low VRAM )
+```
+import torch
+from diffusers import DiffusionPipeline
+from optimum.quanto import freeze, quantize, qint8
+
+model_id = "neuralvfx/LibreFlux-IP-Adapter" 
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype  = torch.bfloat16 if device == "cuda" else torch.float32
+
+pipe = DiffusionPipeline.from_pretrained(
+    model_id,
+    custom_pipeline=model_id,
+    trust_remote_code=True,      
+    torch_dtype=dtype,
+    safety_checker=None         
+)
+print("Loaded:", type(pipe).__name__)  # should be LibreFluxControlNetPipeline
+
+
+# Optional way to download the weights
+hf_hub_download(repo_id="neuralvfx/LibreFlux-IP-Adapter",
+ filename="ip_adapter.pt",
+ local_dir=".",
+ local_dir_use_symlinks=False)
+
+# Load the IP Adapter First
+pipe.load_ip_adapter('ip_adapter.pt')
+
+# Quantize and Freeze
+quantize(
+    pipe.transformer,
+    weights=qint8,
+    exclude=[
+        "*.norm", "*.norm1", "*.norm2", "*.norm2_context",
+        "proj_out", "x_embedder", "norm_out", "context_embedder",
+    ],
+)
+
+quantize(
+    pipe.ip_adapter,
+    weights=qint8,
+    exclude=[
+        "*.norm", "*.norm1", "*.norm2", "*.norm2_context",
+        "proj_out", "x_embedder", "norm_out", "context_embedder",
+    ],
+)
+freeze(pipe.transformer)
+freeze(pipe.ip_adapter)
+
+# Enable Model Offloading
+pipe.enable_model_cpu_offload()
+```