---
title: depth-processor-custom-block
canonical_url: "https://www.modelscope.cn/models/hf-diffusers/depth-processor-custom-block"
md_url: "https://www.modelscope.cn/models/hf-diffusers/depth-processor-custom-block.md"
repository: hf-diffusers/depth-processor-custom-block
last_updated: 2026-02-21
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 87
stars: 0
---

# depth-processor-custom-block

> depth-processor-custom-block - hf-diffusers 在 ModelScope 开源的模型。Depth Processor Block

- **Repository**: hf-diffusers/depth-processor-custom-block
- **Downloads**: 87
- **Stars**: 0
- **Last updated**: 2026-02-21

Source: https://www.modelscope.cn/models/hf-diffusers/depth-processor-custom-block

---

# Depth Processor Block

This is a custom block designed to extract depth maps from input images using the [Depth Anything Model]("https://huggingface.co/depth-anything/Depth-Anything-V2-Large") model. The model can be used as a processor to generate conditioning images for ControlNets.

# How to use

```python
import torch
from diffusers import ModularPipeline, ComponentsManager, ModularPipelineBlocks
from diffusers.utils import load_image

# Use ComponentsManager to enable auto CPU offloading for memory efficiency
manager = ComponentsManager()
manager.enable_auto_cpu_offload(device="cuda:0")


# Initialize pipeline
pipe = ModularPipeline.from_pretrained("Qwen/Qwen-Image", components_manager=manager)

# Insert a depth processing block
blocks = pipe.blocks.get_workflow("controlnet_text2image")
depth_block = ModularPipelineBlocks.from_pretrained(
    "diffusers/depth-processor-custom-block",
    trust_remote_code=True,
)
blocks.sub_blocks.insert("depth", depth_block, 0)

# Reinitialize the pipeline for ControlNet
pipe = blocks.init_pipeline("Qwen/Qwen-Image", components_manager=manager)
pipe.load_components(torch_dtype=torch.bfloat16)

# Load the ControlNet model
controlnet_spec = pipeline.get_component_spec("controlnet")
controlnet_spec.pretrained_model_name_or_path = "InstantX/Qwen-Image-ControlNet-Union"
controlnet = controlnet_spec.load(torch_dtype=torch.bfloat16)
pipe.update_components(controlnet=controlnet)

# Infer
prompt = "cat wizard with red hat, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney"
image = load_image("https://github.com/Trgtuan10/Image_storage/blob/main/cute_cat.png?raw=true")

output = pipe(
    prompt=prompt,
    image=image,
).images[0]
output
```