Revert setuptools pin as k-diffusion pipelines are now deprecated

.github/workflows/pr_tests_gpu.yml

@@ -199,11 +199,6 @@ jobs:
 
     - name: Install dependencies
       run: |
-        # Install pkgs which depend on setuptools<81 for pkg_resources first with no build isolation
-        uv pip install pip==25.2 setuptools==80.10.2
-        uv pip install --no-build-isolation k-diffusion==0.0.12
-        uv pip install --upgrade pip setuptools
-        # Install the rest as normal
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git

.github/workflows/push_tests.yml

@@ -126,11 +126,6 @@ jobs:
 
     - name: Install dependencies
       run: |
-        # Install pkgs which depend on setuptools<81 for pkg_resources first with no build isolation
-        uv pip install pip==25.2 setuptools==80.10.2
-        uv pip install --no-build-isolation k-diffusion==0.0.12
-        uv pip install --upgrade pip setuptools
-        # Install the rest as normal
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git

src/diffusers/models/attention_dispatch.py

@@ -1117,26 +1117,6 @@ def _sage_attention_backward_op(
     raise NotImplementedError("Backward pass is not implemented for Sage attention.")
 
 
-def _maybe_modify_attn_mask_npu(query: torch.Tensor, key: torch.Tensor, attn_mask: torch.Tensor | None = None):
-    # Skip Attention Mask if all values are 1, `None` mask can speedup the computation
-    if attn_mask is not None and torch.all(attn_mask != 0):
-        attn_mask = None
-
-    # Reshape Attention Mask: [batch_size, seq_len_k] -> [batch_size, 1, sqe_len_q, seq_len_k]
-    # https://www.hiascend.com/document/detail/zh/Pytorch/730/apiref/torchnpuCustomsapi/docs/context/torch_npu-npu_fusion_attention.md
-    if (
-        attn_mask is not None
-        and attn_mask.ndim == 2
-        and attn_mask.shape[0] == query.shape[0]
-        and attn_mask.shape[1] == key.shape[1]
-    ):
-        B, Sq, Skv = attn_mask.shape[0], query.shape[1], key.shape[1]
-        attn_mask = ~attn_mask.to(torch.bool)
-        attn_mask = attn_mask.unsqueeze(1).expand(B, Sq, Skv).unsqueeze(1).contiguous()
-
-    return attn_mask
-
-
 def _npu_attention_forward_op(
     ctx: torch.autograd.function.FunctionCtx,
     query: torch.Tensor,
@@ -1154,14 +1134,11 @@ def _npu_attention_forward_op(
     if return_lse:
         raise ValueError("NPU attention backend does not support setting `return_lse=True`.")
 
-    attn_mask = _maybe_modify_attn_mask_npu(query, key, attn_mask)
-
     out = npu_fusion_attention(
         query,
         key,
         value,
         query.size(2),  # num_heads
-        atten_mask=attn_mask,
         input_layout="BSND",
         pse=None,
         scale=1.0 / math.sqrt(query.shape[-1]) if scale is None else scale,
@@ -2691,17 +2668,16 @@ def _native_npu_attention(
     return_lse: bool = False,
     _parallel_config: "ParallelConfig" | None = None,
 ) -> torch.Tensor:
+    if attn_mask is not None:
+        raise ValueError("`attn_mask` is not supported for NPU attention")
     if return_lse:
         raise ValueError("NPU attention backend does not support setting `return_lse=True`.")
     if _parallel_config is None:
-        attn_mask = _maybe_modify_attn_mask_npu(query, key, attn_mask)
-
         out = npu_fusion_attention(
             query,
             key,
             value,
             query.size(2),  # num_heads
-            atten_mask=attn_mask,
             input_layout="BSND",
             pse=None,
             scale=1.0 / math.sqrt(query.shape[-1]) if scale is None else scale,
@@ -2716,7 +2692,7 @@ def _native_npu_attention(
             query,
             key,
             value,
-            attn_mask,
+            None,
             dropout_p,
             None,
             scale,

src/diffusers/models/transformers/transformer_qwenimage.py

@@ -164,11 +164,7 @@ def compute_text_seq_len_from_mask(
     position_ids = torch.arange(text_seq_len, device=encoder_hidden_states.device, dtype=torch.long)
     active_positions = torch.where(encoder_hidden_states_mask, position_ids, position_ids.new_zeros(()))
     has_active = encoder_hidden_states_mask.any(dim=1)
-    per_sample_len = torch.where(
-        has_active,
-        active_positions.max(dim=1).values + 1,
-        torch.as_tensor(text_seq_len, device=encoder_hidden_states.device),
-    )
+    per_sample_len = torch.where(has_active, active_positions.max(dim=1).values + 1, torch.as_tensor(text_seq_len))
     return text_seq_len, per_sample_len, encoder_hidden_states_mask