More diffusers hints

README.md

@@ -37,7 +37,7 @@ LibreFLUX is an Apache 2.0 version of [FLUX.1-schnell](https://huggingface.co/bl
 
 ## Inference
 
-To use the model, just call the custom pipeline using [diffusers](https://github.com/huggingface/diffusers). It currently works with `diffusers==0.30.3` and will be updated to the latest diffusers soon. The model works best with a CFG scale of 2.0 - 5.0, so if you are getting images with a blur or strange shadows try turning down your CFG scale.
+To use the model, just call the custom pipeline using [diffusers](https://github.com/huggingface/diffusers). It currently works with `diffusers==0.30.3` and will be updated to the latest diffusers soon. The model works best with a CFG scale of 2.0 to 5.0, so if you are getting images with a blur or strange shadows try turning down your CFG scale (`guidance_scale` in diffusers). Alternatively, you can also use higher CFG scales if you turn it off during the first couple of timesteps (`no_cfg_until_timestep=2` in the custom pipeline).
 
 ```py
 # ! pip install diffusers==0.30.3
@@ -59,6 +59,10 @@ images = pipe(
   prompt=prompt,
   negative_prompt=negative_prompt,
   return_dict=False,
+  # guidance_scale=3.5,
+  # num_inference_steps=28,
+  # generator=torch.Generator().manual_seed(42),
+  # no_cfg_until_timestep=0,
 )
 images[0][0].save('chalkboard.png')
 
@@ -84,6 +88,10 @@ images = pipe(
   device=None,
   return_dict=False,
   do_batch_cfg=False, # https://github.com/huggingface/optimum-quanto/issues/327
+  # guidance_scale=3.5,
+  # num_inference_steps=28,
+  # generator=torch.Generator().manual_seed(42),
+  # no_cfg_until_timestep=0,
 )
 images[0][0].save('chalkboard.png')
 ```