Flux fp16 inference fix

docs/source/en/api/pipelines/flux.md

@@ -37,7 +37,7 @@ Both checkpoints have slightly difference usage which we detail below.
 
 ```python
 import torch
-from diffusers import  FluxPipeline
+from diffusers import FluxPipeline
 
 pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16)
 pipe.enable_model_cpu_offload()
@@ -61,7 +61,7 @@ out.save("image.png")
 
 ```python
 import torch
-from diffusers import  FluxPipeline
+from diffusers import FluxPipeline
 
 pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
 pipe.enable_model_cpu_offload()

src/diffusers/models/transformers/transformer_flux.py

@@ -125,6 +125,8 @@ def forward(
         gate = gate.unsqueeze(1)
         hidden_states = gate * self.proj_out(hidden_states)
         hidden_states = residual + hidden_states
+        if hidden_states.dtype == torch.float16:
+            hidden_states = hidden_states.clip(-65504, 65504)
 
         return hidden_states
 
@@ -223,6 +225,8 @@ def forward(
 
         context_ff_output = self.ff_context(norm_encoder_hidden_states)
         encoder_hidden_states = encoder_hidden_states + c_gate_mlp.unsqueeze(1) * context_ff_output
+        if encoder_hidden_states.dtype == torch.float16:
+            encoder_hidden_states = encoder_hidden_states.clip(-65504, 65504)
 
         return encoder_hidden_states, hidden_states