Instructions to use xvjiarui/IMProv-v1-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xvjiarui/IMProv-v1-0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xvjiarui/IMProv-v1-0", 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
Download image_decoder/config.json from xvjiarui/IMProv-v1-0: direct link, hf CLI and curl.
- Browser
- Download file 436 Bytes
-
https://huggingface.co/xvjiarui/IMProv-v1-0/resolve/main/image_decoder/config.json
- Command line
-
hf download hf://xvjiarui/IMProv-v1-0/image_decoder/config.json
-
curl -L -o config.json https://huggingface.co/xvjiarui/IMProv-v1-0/resolve/main/image_decoder/config.json
436 Bytes
| { | |
| "_class_name": "VQDecoder", | |
| "_diffusers_version": "0.24.0", | |
| "_name_or_path": "/shared/jiarui/results/video-diffusers/output/mae_p16_text_ed_enc_cat_n1024_arxiv_l400m_224_600k_bs1024x8/amp/hf_pipeline/image_decoder", | |
| "codebook_size": 1024, | |
| "pixel_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "pixel_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "pretrained_model_name_or_path": "xvjiarui/taming-vq-f16-n1024", | |
| "scale_factor": 16 | |
| } | |