Instructions to use Nap/depth_anything_v2_vitg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Nap/depth_anything_v2_vitg with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Nap/depth_anything_v2_vitg", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Commit History
-
Delete modified code. Since Kijai added support for the giant model, no modifications are needed.
Verified signature0abc420 -
Update README.md
Verified signatureFix formatting.127fa0a -
Update README.md
Verified signatureRemove previous instructions for running in ComfyUI. Since Kijai added support for the giant model, no modifications are needed.dd4b96c -
Update README.md
Verified signature33ee683 -
Modified version of Kijai's ComfyUI-DepthAnythingV2 custom nodes
Verified signatureModified version of Kijai's ComfyUI-DepthAnythingV2 custom nodes that will work with depth_anything_v2_vitg_fp32.safetensors. Just replace the ComfyUI/custom_nodes/comfyui-depthanythingv2/nodes.py file with this one and ensure depth_anything_v2_vitg_fp32.safetensors is in the ComfyUI/models/depthanything/ folder, as it will not be downloaded automatically.f9441d0 -
Update README.md
Verified signature029d229 -
Upload depth_anything_v2_vitg_fp32.safetensors
Verified signatureDepth Anything V2 Giant - 1.3B params - FP32 - Converted from .pth to .safetensors11a567b -
initial commit
Verified signature7cc06b6