Update After RCFG experiment

- Update readme to log the RCFG experiment
- Refactor code
- Add delta parameter on Animate_Anyone_Sampler node
- Add ComfyUI Sampler progress bar

_test.py

@@ -1,13 +1,38 @@
-import inspect
-from diffusers.schedulers import (
-    DDIMScheduler,
-    DPMSolverMultistepScheduler,
-    LCMScheduler,
-    EulerDiscreteScheduler,
-    EulerAncestralDiscreteScheduler,
-    LMSDiscreteScheduler,
-    PNDMScheduler,
-)
+import time
+import torch
+from diffusers import (StableDiffusionPipeline,
+                       EulerAncestralDiscreteScheduler)
+from sfast.compilers.diffusion_pipeline_compiler import (compile,
+                                                         CompilationConfig)
 
-print("clip_samples" in inspect.signature(DDIMScheduler.__init__).parameters)
-    
+def load_model():
+    model = StableDiffusionPipeline.from_pretrained(
+        'runwayml/stable-diffusion-v1-5',
+        torch_dtype=torch.float16)
+
+    model.scheduler = EulerAncestralDiscreteScheduler.from_config(
+        model.scheduler.config)
+    model.safety_checker = None
+    model.to(torch.device('cuda'))
+    return model
+
+model = load_model()
+
+config = CompilationConfig.Default()
+# xformers and Triton are suggested for achieving best performance.
+try:
+    import xformers
+    config.enable_xformers = True
+except ImportError:
+    print('xformers not installed, skip')
+try:
+    import triton
+    config.enable_triton = True
+except ImportError:
+    print('Triton not installed, skip')
+# CUDA Graph is suggested for small batch sizes and small resolutions to reduce CPU overhead.
+# But it can increase the amount of GPU memory used.
+# For StableVideoDiffusionPipeline it is not needed.
+config.enable_cuda_graph = True
+
+model = compile(model, config)