Buckets:
| # ComponentsManager | |
| > [!WARNING] | |
| > [ComponentsManager](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager) 仍处于积极开发阶段，其 API 可能会发生变化。 | |
| [ComponentsManager](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager) 是 Modular Diffusers 的模型注册与管理系统。它负责添加和跟踪模型，存储有用的元数据（模型大小、设备放置、适配器），并支持卸载。 | |
| 本指南将向您展示如何使用 [ComponentsManager](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager) 来管理组件和设备内存。 | |
| ## 连接到管道 | |
| Create a [ComponentsManager](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager) and pass it to a [ModularPipeline](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline#diffusers.ModularPipeline) with either [from_pretrained()](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline#diffusers.ModularPipeline.from_pretrained) or [init_pipeline()](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_blocks#diffusers.ModularPipelineBlocks.init_pipeline). | |
| ```py | |
| from diffusers import ModularPipeline, ComponentsManager | |
| import torch | |
| manager = ComponentsManager() | |
| pipe = ModularPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", components_manager=manager) | |
| pipe.load_components(dtype=torch.bfloat16) | |
| ``` | |
| ```py | |
| from diffusers import ModularPipelineBlocks, ComponentsManager | |
| import torch | |
| manager = ComponentsManager() | |
| blocks = ModularPipelineBlocks.from_pretrained("diffusers/Florence2-image-Annotator", trust_remote_code=True) | |
| pipe= blocks.init_pipeline(components_manager=manager) | |
| pipe.load_components(dtype=torch.bfloat16) | |
| ``` | |
| 由 pipeline 加载的组件会自动注册到管理器中。您可以立即查看它们。 | |
| ## 检查组件 | |
| 打印 [ComponentsManager](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager) 以查看所有已注册的组件，包括其类、设备放置、dtype、内存大小和加载 ID。 | |
| 以下输出对应于上述 `from_pretrained` 示例。 | |
| ```py | |
| Components: | |
| ============================================================================================================================= | |
| Models: | |
| ----------------------------------------------------------------------------------------------------------------------------- | |
| Name_ID | Class | Device: act(exec) | Dtype | Size (GB) | Load ID | |
| ----------------------------------------------------------------------------------------------------------------------------- | |
| text_encoder_140458257514752 | Qwen3Model | cpu | torch.bfloat16 | 7.49 | Tongyi-MAI/Z-Image-Turbo|text_encoder|null|null | |
| vae_140458257515376 | AutoencoderKL | cpu | torch.bfloat16 | 0.16 | Tongyi-MAI/Z-Image-Turbo|vae|null|null | |
| transformer_140458257515616 | ZImageTransformer2DModel | cpu | torch.bfloat16 | 11.46 | Tongyi-MAI/Z-Image-Turbo|transformer|null|null | |
| ----------------------------------------------------------------------------------------------------------------------------- | |
| Other Components: | |
| ----------------------------------------------------------------------------------------------------------------------------- | |
| ID | Class | Collection | |
| ----------------------------------------------------------------------------------------------------------------------------- | |
| scheduler_140461023555264 | FlowMatchEulerDiscreteScheduler | N/A | |
| tokenizer_140458256346432 | Qwen2Tokenizer | N/A | |
| ----------------------------------------------------------------------------------------------------------------------------- | |
| ``` | |
| 该表格将模型（包含设备、dtype 和内存信息）与其他组件（如调度器和分词器）分开显示。如果任何模型应用了 LoRA 适配器、IP-Adapter 或量化，相关信息将在底部的附加部分中显示。 | |
| ## 卸载 | |
| [enable_auto_cpu_offload()](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager.enable_auto_cpu_offload) 方法是一种全局卸载策略，可跨所有模型生效，无论它们被哪个 pipeline 使用。启用后，即使添加或移除组件，您也无需担心设备放置问题。 | |
| ```py | |
| manager.enable_auto_cpu_offload(device="cuda") # or "mps", "xpu", "cpu" | |
| ``` | |
| 所有模型最初都位于 CPU 上，[ComponentsManager](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager) 会在模型即将被使用之前将其移动到合适的设备上，并在 GPU 内存不足时将其他模型移回 CPU。 | |
| 调用 [disable_auto_cpu_offload()](/docs/diffusers/v0.43.0/zh/api/modular_diffusers/pipeline_components#diffusers.ComponentsManager.disable_auto_cpu_offload) 以禁用卸载。 | |
| ```py | |
| manager.disable_auto_cpu_offload() | |
| ``` | |
Xet Storage Details
- Size:
- 5.11 kB
- Xet hash:
- 7d148f6c5e0bdbfa9c76ad65f4f605e165ede12d925dc9d1ebbf651ed541e65f
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.