update

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

@@ -77,21 +77,10 @@ CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds o
 - `pipe.enable_model_cpu_offload()`:
   - Without enabling cpu offloading, memory usage is `33 GB`
   - With enabling cpu offloading, memory usage is `19 GB`
-- `pipe.enable_sequential_cpu_offload()`:
-  - Similar to `enable_model_cpu_offload` but can significantly reduce memory usage at the cost of slow inference
-  - When enabled, memory usage is under `4 GB`
 - `pipe.vae.enable_tiling()`:
   - With enabling cpu offloading and tiling, memory usage is `11 GB`
 - `pipe.vae.enable_slicing()`
 
-### Quantized inference
-
-[torchao](https://github.com/pytorch/ao) and [optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be used to quantize the text encoder, transformer and VAE modules to lower the memory requirements. This makes it possible to run the model on a free-tier T4 Colab or lower VRAM GPUs!
-
-It is also worth noting that torchao quantization is fully compatible with [torch.compile](/optimization/torch2.0#torchcompile), which allows for much faster inference speed. Additionally, models can be serialized and stored in a quantized datatype to save disk space with torchao. Find examples and benchmarks in the gists below.
-- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
-- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
-
 ## CogVideoXPipeline
 
 [[autodoc]] CogVideoXPipeline

src/diffusers/loaders/single_file_utils.py

@@ -91,11 +91,11 @@ DIFFUSERS_DEFAULT_PIPELINE_PATHS = {
     "xl_inpaint": {"pretrained_model_name_or_path": "diffusers/stable-diffusion-xl-1.0-inpainting-0.1"},
     "playground-v2-5": {"pretrained_model_name_or_path": "playgroundai/playground-v2.5-1024px-aesthetic"},
     "upscale": {"pretrained_model_name_or_path": "stabilityai/stable-diffusion-x4-upscaler"},
-    "inpainting": {"pretrained_model_name_or_path": "Lykon/dreamshaper-8-inpainting"},
+    "inpainting": {"pretrained_model_name_or_path": "runwayml/stable-diffusion-inpainting"},
     "inpainting_v2": {"pretrained_model_name_or_path": "stabilityai/stable-diffusion-2-inpainting"},
     "controlnet": {"pretrained_model_name_or_path": "lllyasviel/control_v11p_sd15_canny"},
     "v2": {"pretrained_model_name_or_path": "stabilityai/stable-diffusion-2-1"},
-    "v1": {"pretrained_model_name_or_path": "Lykon/dreamshaper-8"},
+    "v1": {"pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5"},
     "stable_cascade_stage_b": {"pretrained_model_name_or_path": "stabilityai/stable-cascade", "subfolder": "decoder"},
     "stable_cascade_stage_b_lite": {
         "pretrained_model_name_or_path": "stabilityai/stable-cascade",

src/diffusers/models/embeddings.py

@@ -545,14 +545,11 @@ def get_1d_rotary_pos_embed(
     assert dim % 2 == 0
 
     if isinstance(pos, int):
-        pos = torch.arange(pos)
-    if isinstance(pos, np.ndarray):
-        pos = torch.from_numpy(pos)  # type: ignore  # [S]
-
+        pos = np.arange(pos)
     theta = theta * ntk_factor
     freqs = 1.0 / (theta ** (torch.arange(0, dim, 2, dtype=freqs_dtype)[: (dim // 2)] / dim)) / linear_factor  # [D/2]
-    freqs = freqs.to(pos.device)
-    freqs = torch.outer(pos, freqs)  # type: ignore   # [S, D/2]
+    t = torch.from_numpy(pos).to(freqs.device)  # type: ignore  # [S]
+    freqs = torch.outer(t, freqs)  # type: ignore   # [S, D/2]
     if use_real and repeat_interleave_real:
         # flux, hunyuan-dit, cogvideox
         freqs_cos = freqs.cos().repeat_interleave(2, dim=1).float()  # [S, D]
@@ -629,7 +626,7 @@ class FluxPosEmbed(nn.Module):
         n_axes = ids.shape[-1]
         cos_out = []
         sin_out = []
-        pos = ids.squeeze().float()
+        pos = ids.squeeze().float().cpu().numpy()
         is_mps = ids.device.type == "mps"
         freqs_dtype = torch.float32 if is_mps else torch.float64
         for i in range(n_axes):

tests/models/test_modeling_common.py

@@ -417,9 +417,6 @@ class ModelTesterMixin:
 
     @require_torch_gpu
     def test_set_attn_processor_for_determinism(self):
-        if self.uses_custom_attn_processor:
-            return
-
         torch.use_deterministic_algorithms(False)
         if self.forward_requires_fresh_args:
             model = self.model_class(**self.init_dict)

tests/models/transformers/test_models_transformer_flux.py

@@ -32,9 +32,6 @@ class FluxTransformerTests(ModelTesterMixin, unittest.TestCase):
     # We override the items here because the transformer under consideration is small.
     model_split_percents = [0.7, 0.6, 0.6]
 
-    # Skip setting testing with default: AttnProcessor
-    uses_custom_attn_processor = True
-
     @property
     def dummy_input(self):
         batch_size = 1

tests/pipelines/flux/test_pipeline_flux.py

@@ -25,9 +25,6 @@ class FluxPipelineFastTests(unittest.TestCase, PipelineTesterMixin):
     params = frozenset(["prompt", "height", "width", "guidance_scale", "prompt_embeds", "pooled_prompt_embeds"])
     batch_params = frozenset(["prompt"])
 
-    # there is no xformers processor for Flux
-    test_xformers_attention = False
-
     def get_dummy_components(self):
         torch.manual_seed(0)
         transformer = FluxTransformer2DModel(

tests/pipelines/pag/test_pag_sd3.py

@@ -37,7 +37,6 @@ class StableDiffusion3PAGPipelineFastTests(unittest.TestCase, PipelineTesterMixi
         ]
     )
     batch_params = frozenset(["prompt", "negative_prompt"])
-    test_xformers_attention = False
 
     def get_dummy_components(self):
         torch.manual_seed(0)

tests/pipelines/stable_audio/test_stable_audio.py

@@ -68,8 +68,6 @@ class StableAudioPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
             "callback_steps",
         ]
     )
-    # There is not xformers version of the StableAudioPipeline custom attention processor
-    test_xformers_attention = False
 
     def get_dummy_components(self):
         torch.manual_seed(0)