update

.ai/AGENTS.md

@@ -1,71 +0,0 @@
-# Diffusers — Agent Guide
-
-### Philosophy
-
-Write code as simple and explicit as possible.
-
-- Minimize small helper/utility functions — inline the logic instead. A reader should be able to follow the full flow without jumping between functions.
-- No defensive code or unused code paths — do not add fallback paths, safety checks, or configuration options "just in case". When porting from a research repo, delete training-time code paths, experimental flags, and ablation branches entirely — only keep the inference path you are actually integrating.
-- Do not guess user intent and silently correct behavior. Make the expected inputs clear in the docstring, and raise a concise error for unsupported cases rather than adding complex fallback logic.
-
----
-
-### Dependencies
-- No new mandatory dependency without discussion (e.g. `einops`)
-- Optional deps guarded with `is_X_available()` and a dummy in `utils/dummy_*.py`
-
-### Code Style
-- `make style` and `make fix-copies` should be run as the final step before opening a PR
-
-### Copied Code
-- Many classes are kept in sync with a source via a `# Copied from ...` header comment
-- Do not edit a `# Copied from` block directly — run `make fix-copies` to propagate changes from the source
-- Remove the header to intentionally break the link
-
-### Models
-- All layer calls should be visible directly in `forward` — avoid helper functions that hide `nn.Module` calls.
-- Attention must follow the diffusers pattern: both the `Attention` class and its processor are defined in the model file. The processor's `__call__` handles the actual compute and must use `dispatch_attention_fn` rather than calling `F.scaled_dot_product_attention` directly. The attention class inherits `AttentionModuleMixin` and declares `_default_processor_cls` and `_available_processors`.
-
-```python
-# transformer_mymodel.py
-
-class MyModelAttnProcessor:
-    _attention_backend = None
-    _parallel_config = None
-
-    def __call__(self, attn, hidden_states, attention_mask=None, ...):
-        query = attn.to_q(hidden_states)
-        key = attn.to_k(hidden_states)
-        value = attn.to_v(hidden_states)
-        # reshape, apply rope, etc.
-        hidden_states = dispatch_attention_fn(
-            query, key, value,
-            attn_mask=attention_mask,
-            backend=self._attention_backend,
-            parallel_config=self._parallel_config,
-        )
-        hidden_states = hidden_states.flatten(2, 3)
-        return attn.to_out[0](hidden_states)
-
-
-class MyModelAttention(nn.Module, AttentionModuleMixin):
-    _default_processor_cls = MyModelAttnProcessor
-    _available_processors = [MyModelAttnProcessor]
-
-    def __init__(self, query_dim, heads=8, dim_head=64, ...):
-        super().__init__()
-        self.to_q = nn.Linear(query_dim, heads * dim_head, bias=False)
-        self.to_k = nn.Linear(query_dim, heads * dim_head, bias=False)
-        self.to_v = nn.Linear(query_dim, heads * dim_head, bias=False)
-        self.to_out = nn.ModuleList([nn.Linear(heads * dim_head, query_dim), nn.Dropout(0.0)])
-        self.set_processor(MyModelAttnProcessor())
-
-    def forward(self, hidden_states, attention_mask=None, **kwargs):
-        return self.processor(self, hidden_states, attention_mask, **kwargs)
-```
-
-### Pipeline
-- All pipelines must inherit from `DiffusionPipeline`
-
-### Tests
-- Slow tests gated with `@slow` and `RUN_SLOW=1`

.gitignore

@@ -178,8 +178,4 @@ tags
 .ruff_cache
 
 # wandb
-wandb
-
-# AI agent generated symlinks
-/AGENTS.md
-/CLAUDE.md
+wandb

Makefile

@@ -1,4 +1,4 @@
-.PHONY: deps_table_update modified_only_fixup extra_style_checks quality style fixup fix-copies test test-examples codex claude clean-ai
+.PHONY: deps_table_update modified_only_fixup extra_style_checks quality style fixup fix-copies test test-examples
 
 # make sure to test the local checkout in scripts and not the pre-installed one (don't use quotes!)
 export PYTHONPATH = src
@@ -98,14 +98,3 @@ post-release:
 
 post-patch:
 	python utils/release.py --post_release --patch
-
-# AI agent symlinks
-
-codex:
-	ln -snf .ai/AGENTS.md AGENTS.md
-
-claude:
-	ln -snf .ai/AGENTS.md CLAUDE.md
-
-clean-ai:
-	rm -f AGENTS.md CLAUDE.md

docs/source/en/_toctree.yml

@@ -532,6 +532,8 @@
         title: ControlNet-XS with Stable Diffusion XL
       - local: api/pipelines/controlnet_union
         title: ControlNetUnion
+      - local: api/pipelines/cosmos
+        title: Cosmos
       - local: api/pipelines/ddim
         title: DDIM
       - local: api/pipelines/ddpm
@@ -675,8 +677,6 @@
         title: CogVideoX
       - local: api/pipelines/consisid
         title: ConsisID
-      - local: api/pipelines/cosmos
-        title: Cosmos
       - local: api/pipelines/framepack
         title: Framepack
       - local: api/pipelines/helios

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

@@ -21,31 +21,29 @@
 > [!TIP]
 > Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
-## Basic usage
+## Loading original format checkpoints
+
+Original format checkpoints that have not been converted to diffusers-expected format can be loaded using the `from_single_file` method.
 
 ```python
 import torch
-from diffusers import Cosmos2_5_PredictBasePipeline
-from diffusers.utils import export_to_video
+from diffusers import Cosmos2TextToImagePipeline, CosmosTransformer3DModel
 
-model_id = "nvidia/Cosmos-Predict2.5-2B"
-pipe = Cosmos2_5_PredictBasePipeline.from_pretrained(
-    model_id, revision="diffusers/base/post-trained", torch_dtype=torch.bfloat16
-)
+model_id = "nvidia/Cosmos-Predict2-2B-Text2Image"
+transformer = CosmosTransformer3DModel.from_single_file(
+    "https://huggingface.co/nvidia/Cosmos-Predict2-2B-Text2Image/blob/main/model.pt",
+    torch_dtype=torch.bfloat16,
+).to("cuda")
+pipe = Cosmos2TextToImagePipeline.from_pretrained(model_id, transformer=transformer, torch_dtype=torch.bfloat16)
 pipe.to("cuda")
 
-prompt = "As the red light shifts to green, the red bus at the intersection begins to move forward, its headlights cutting through the falling snow. The snowy tire tracks deepen as the vehicle inches ahead, casting fresh lines onto the slushy road. Around it, streetlights glow warmer, illuminating the drifting flakes and wet reflections on the asphalt. Other cars behind start to edge forward, their beams joining the scene. The stillness of the urban street transitions into motion as the quiet snowfall is punctuated by the slow advance of traffic through the frosty city corridor."
+prompt = "A close-up shot captures a vibrant yellow scrubber vigorously working on a grimy plate, its bristles moving in circular motions to lift stubborn grease and food residue. The dish, once covered in remnants of a hearty meal, gradually reveals its original glossy surface. Suds form and bubble around the scrubber, creating a satisfying visual of cleanliness in progress. The sound of scrubbing fills the air, accompanied by the gentle clinking of the dish against the sink. As the scrubber continues its task, the dish transforms, gleaming under the bright kitchen lights, symbolizing the triumph of cleanliness over mess."
 negative_prompt = "The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality."
 
 output = pipe(
-    image=None,
-    video=None,
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    num_frames=93,
-    generator=torch.Generator().manual_seed(1),
-).frames[0]
-export_to_video(output, "text2world.mp4", fps=16)
+    prompt=prompt, negative_prompt=negative_prompt, generator=torch.Generator().manual_seed(1)
+).images[0]
+output.save("output.png")
 ```
 
 ## Cosmos2_5_TransferPipeline

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

@@ -44,7 +44,6 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [ControlNet with Stable Diffusion XL](controlnet_sdxl) | text2image |
 | [ControlNet-XS](controlnetxs) | text2image |
 | [ControlNet-XS with Stable Diffusion XL](controlnetxs_sdxl) | text2image |
-| [Cosmos](cosmos) | text2video, video2video |
 | [Dance Diffusion](dance_diffusion) | unconditional audio generation |
 | [DDIM](ddim) | unconditional image generation |
 | [DDPM](ddpm) | unconditional image generation |

docs/source/en/conceptual/contribution.md

@@ -565,16 +565,4 @@ $ git push --set-upstream origin your-branch-for-syncing
 
 ### Style guide
 
-For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).
-
-
-## Coding with AI agents
-
-The repository keeps AI-agent configuration in `.ai/` and exposes local agent files via symlinks.
-
-- **Source of truth** — edit `.ai/AGENTS.md` (and any future `.ai/skills/`)
-- **Don't edit** generated root-level `AGENTS.md` or `CLAUDE.md` — they are symlinks
-- Setup commands:
-  - `make codex` — symlink for OpenAI Codex
-  - `make claude` — symlink for Claude Code
-  - `make clean-ai` — remove generated symlinks
+For documentation strings, 🧨 Diffusers follows the [Google style](https://google.github.io/styleguide/pyguide.html).

src/diffusers/modular_pipelines/modular_pipeline.py

@@ -14,6 +14,7 @@
 import importlib
 import inspect
 import os
+import shutil
 import sys
 import traceback
 import warnings
@@ -1883,6 +1884,36 @@ class ModularPipeline(ConfigMixin, PushToHubMixin):
         )
         return pipeline
 
+    def _maybe_save_custom_code(self, save_directory: str | os.PathLike):
+        """Save custom code files (blocks config and Python modules) to the save directory."""
+        if self._blocks is None:
+            return
+
+        blocks_module = type(self._blocks).__module__
+        is_custom_code = not blocks_module.startswith("diffusers.") and blocks_module != "diffusers"
+        if not is_custom_code:
+            return
+
+        os.makedirs(save_directory, exist_ok=True)
+
+        self._blocks.save_pretrained(save_directory)
+
+        source_file = inspect.getfile(type(self._blocks))
+        module_file = os.path.basename(source_file)
+        dest_file = os.path.join(save_directory, module_file)
+
+        if os.path.abspath(source_file) != os.path.abspath(dest_file):
+            shutil.copyfile(source_file, dest_file)
+
+        from ..utils.dynamic_modules_utils import get_relative_import_files
+
+        for rel_file in get_relative_import_files(source_file):
+            rel_name = os.path.relpath(rel_file, os.path.dirname(source_file))
+            rel_dest = os.path.join(save_directory, rel_name)
+            if os.path.abspath(rel_file) != os.path.abspath(rel_dest):
+                os.makedirs(os.path.dirname(rel_dest), exist_ok=True)
+                shutil.copyfile(rel_file, rel_dest)
+
     def save_pretrained(
         self,
         save_directory: str | os.PathLike,
@@ -1998,6 +2029,8 @@ class ModularPipeline(ConfigMixin, PushToHubMixin):
                 component_spec_dict["subfolder"] = component_name
                 self.register_to_config(**{component_name: (library, class_name, component_spec_dict)})
 
+        self._maybe_save_custom_code(save_directory)
+
         self.save_config(save_directory=save_directory)
 
         if push_to_hub:

src/diffusers/pipelines/cosmos/pipeline_cosmos2_5_transfer.py

@@ -82,16 +82,13 @@ EXAMPLE_DOC_STRING = """
         ```python
         >>> import cv2
         >>> import numpy as np
-        >>> from PIL import Image
         >>> import torch
         >>> from diffusers import Cosmos2_5_TransferPipeline, AutoModel
         >>> from diffusers.utils import export_to_video, load_video
 
         >>> model_id = "nvidia/Cosmos-Transfer2.5-2B"
         >>> # Load a Transfer2.5 controlnet variant (edge, depth, seg, or blur)
-        >>> controlnet = AutoModel.from_pretrained(
-        ...     model_id, revision="diffusers/controlnet/general/edge", torch_dtype=torch.bfloat16
-        ... )
+        >>> controlnet = AutoModel.from_pretrained(model_id, revision="diffusers/controlnet/general/edge")
         >>> pipe = Cosmos2_5_TransferPipeline.from_pretrained(
         ...     model_id, controlnet=controlnet, revision="diffusers/general", torch_dtype=torch.bfloat16
         ... )