Downloads · 30 days
144
1% of all-time downloads
controlnet-v1e-sdxl-depth
SargeZT/controlnet-v1e-sdxl-depth
controlnet-v1e-sdxl-depth is a text-to-image model from SargeZT. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with depth maps. Note that the input depth maps are perceptually mapped from ZoeDepth. You can find some example images below. prompt: n…
All-time downloads
11.1K
Public
Parameters
1.3B
15 GB on disk
Likes
36
Public
Repo makeup
Click a slice to open those files.
.bin5 GB · 50%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Jul 29, 2023
- Updated
- Aug 5, 2023
- SHA
- 9adc48d5
Base models
Model card
From the Hugging Face model README
controlnet-SargeZT/controlnet-v1e-sdxl-depth
These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with depth maps. Note that the input depth maps are perceptually mapped from ZoeDepth.
You can find some example images below.
prompt: nightmare construction worker, unsettling
prompt: android warrior, unsettling
License
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Created
- Jul 29, 2023
- Updated
- Aug 5, 2023