Fix wrong conditioning used (#3595)

As it said in comment to this branch we want to use conditioning run:
```python
if cfg_injection:  # only applying ControlNet to conditional instead of in unconditioned
```
But in code used unconditioning
embeddings(`conditioning_data.unconditioned_embeddings`).

Later in code confirms that we want to run conditioning generation by
comment and tensor concatenation order(as all code expect to get [uc, c]
tensor):
```python
if cfg_injection:
    # Inferred ControlNet only for the conditional batch.
    # To apply the output of ControlNet to both the unconditional and conditional batches,
    #   add 0 to the unconditional batch to keep it unchanged.
    down_samples = [torch.cat([torch.zeros_like(d), d]) for d in down_samples]
    mid_sample = torch.cat([torch.zeros_like(mid_sample), mid_sample])
```

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -631,7 +631,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
                         control_latent_input = torch.cat([unet_latent_input] * 2)
 
                     if cfg_injection:  # only applying ControlNet to conditional instead of in unconditioned
-                        encoder_hidden_states = torch.cat([conditioning_data.unconditioned_embeddings])
+                        encoder_hidden_states = conditioning_data.text_embeddings
                     else:
                         encoder_hidden_states = torch.cat([conditioning_data.unconditioned_embeddings,
                                                            conditioning_data.text_embeddings])