Text-to-Image
Diffusers
Safetensors
English
Chinese
QwenImage21Pipeline
bitsandbytes
int8
image-generation
image-editing
rgba
8-bit precision
Instructions to use ixim/Image21-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ixim/Image21-INT8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ixim/Image21-INT8", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Download evaluation/young_woman/comparison.csv from ixim/Image21-INT8: direct link, hf CLI and curl.
- Browser
- Download file 510 Bytes
-
https://huggingface.co/ixim/Image21-INT8/resolve/main/evaluation/young_woman/comparison.csv
- Command line
-
hf download hf://ixim/Image21-INT8/evaluation/young_woman/comparison.csv
-
curl -L -o comparison.csv https://huggingface.co/ixim/Image21-INT8/resolve/main/evaluation/young_woman/comparison.csv
510 Bytes
| case_id,seed,bf16_seconds,int8_seconds,speed_ratio_bf16_over_int8,bf16_peak_allocated_gib,int8_peak_allocated_gib,rgb_mae_white,rgb_psnr_white_db,alpha_mae | |
| young_chinese_woman,42,28.578781700000036,19.578480000000127,1.4597038023380697,16.444443225860596,9.529117107391357,0.010024778544902802,31.41698381919181,0.00012096697173547 | |
| young_chinese_woman,123,26.632947500000228,19.441281499999604,1.3699172814302787,16.444443225860596,9.529117107391357,0.00630606384947896,35.93723710368233,9.255874465452507e-05 | |