Update README.md

README.md

@@ -6,8 +6,57 @@ Standalone inference pipeline for LibreFLUX-based ControlNet with classifier-fre
 ## Status
 Work in progress. Not fully functional yet. Code is being transferred and adapted from my larger project repo to this inference-only repo.
 
-## Planned
-- Single image plus prompt inference with CFG
-- Negative prompts and control strength
-- Simple batch mode via JSONL
-- Minimal example inputs
+
+### Compatibility
+
+- Use these specific library versions:
+```
+pip install -U diffusers==0.32.0
+pip install -U "transformers @ git+https://github.com/huggingface/transformers@e15687fffe5c9d20598a19aeab721ae0a7580f8a"
+```
+
+### Load Pipeline
+
+```import torch
+from diffusers import DiffusionPipeline
+
+model_id = "neuralvfx/LibreFlux-ControlNet"  
+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        
+).to(device)
+```
+
+### Inference
+
+```from PIL import Image
+# Load Control Image
+cond = Image.open("examples/libe_flux_control.png")
+cond = cond.resize((1024, 1024))
+
+# Convert PIL image to tensor and move to device with correct dtype
+cond_tensor = ToTensor()(cond)[:3,:,:].to(pipe.device, dtype=pipe.dtype).unsqueeze(0)
+
+out = pipe(
+  prompt="many pieces of drift wood spelling libre flux sitting casting shadow on the lumpy sandy beach with foot prints all over it",
+            negative_prompt="blurry",
+            control_image=cond_tensor,  # Use the tensor here
+            num_inference_steps=75,
+            guidance_scale=4.0,
+            height =1024,
+            width=1024,
+            controlnet_conditioning_scale=1.0,
+            num_images_per_prompt=1,
+            control_mode=None,
+            generator= torch.Generator().manual_seed(32),
+            return_dict=True,
+        )
+out.images[0]
+```