fix: preserve boolean dtype for attention masks in ChromaPipeline

- Convert attention masks to bool and prevent dtype corruption
- Fix both positive and negative mask handling in _get_t5_prompt_embeds
- Remove float conversion in _prepare_attention_mask method

Fixes #12116

Author: akshay-babbar

src/diffusers/pipelines/chroma/pipeline_chroma.py

@@ -233,19 +233,20 @@ def _get_t5_prompt_embeds(
         )
         text_input_ids = text_inputs.input_ids
         attention_mask = text_inputs.attention_mask.clone()
+        attention_mask = attention_mask.bool()  # fix here mine
 
         # Chroma requires the attention mask to include one padding token
         seq_lengths = attention_mask.sum(dim=1)
         mask_indices = torch.arange(attention_mask.size(1)).unsqueeze(0).expand(batch_size, -1)
-        attention_mask = (mask_indices <= seq_lengths.unsqueeze(1)).long()
+        attention_mask = (mask_indices <= seq_lengths.unsqueeze(1)).bool()
 
         prompt_embeds = self.text_encoder(
             text_input_ids.to(device), output_hidden_states=False, attention_mask=attention_mask.to(device)
         )[0]
 
         dtype = self.text_encoder.dtype
         prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)
-        attention_mask = attention_mask.to(dtype=dtype, device=device)
+        attention_mask = attention_mask.to(device=device)
 
         _, seq_len, _ = prompt_embeds.shape
 
@@ -580,10 +581,10 @@ def _prepare_attention_mask(
 
         # Extend the prompt attention mask to account for image tokens in the final sequence
         attention_mask = torch.cat(
-            [attention_mask, torch.ones(batch_size, sequence_length, device=attention_mask.device)],
+            [attention_mask, torch.ones(batch_size, sequence_length, device=attention_mask.device, dtype=torch.bool)],
             dim=1,
         )
-        attention_mask = attention_mask.to(dtype)
+        # attention_mask = attention_mask.to(dtype)
 
         return attention_mask