Model reference · open weights
controlnet-openpose-sdxl-1.0 is an open-weight image model from xinsir, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
State of the art ControlNet-openpose-sdxl-1.0 model, below are the result for midjourney and anime, just for show controlnet-openpose-sdxl-1.0 - Developed by: xinsir - Model type: ControlNetSDXL - License: apache-2.0 - Finetuned from model [optional]: stabilityai/stable-diffusion-xl-base-1.0 Model Sources [optional] - Paper [optional]: https://arxiv.org/abs/2302.05543 - Examples Replace the default draw pose function to get better result thanks feiyuuu for report the problem. When using the default pose line the performance may be unstable, this is because the pose label use more thick line in training to have a better look. This difference can be fix by using the following method: Find the util.py in controlnetaux python package, usually the path is like: /your anaconda3 path/envs/your env name/lib/python3.8/site-packages/controlnetaux/openpose/util.py Replace the drawbodypose function with the following code: How to Get Started with the Model Use the code below to get started with the model. Evaluation Data HumanArt [https://github.com/IDEA-Research/HumanArt], select 2000 images with ground truth pose annotations to generate images and calculate mAP. Quantitative Result We are the SOTA openpose model compared with other opensource models.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | xinsir |
|---|---|
| Type | Image models |
| Parameters (lead) | 1.3B |
| Variants | 1 |
| Runs with | diffusers |
| Released | 2024-05-13 |
| Popularity | 109k downloads / month |
| Likes | 310 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| controlnet-openpose-sdxl-1.0 | 1.3B | BF16 | ~2.9 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys controlnet-openpose-sdxl-1-0 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (controlnet-openpose-sdxl-1-0 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"controlnet-openpose-sdxl-1-0","prompt":"a red bicycle","size":"1024x1024"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗