Text-to-Image
Diffusers
Safetensors
QwenImage21Pipeline
image-generation
image-editing
bitsandbytes
int8
qwen-image-2.1-turbo
8-bit precision
Instructions to use ixim/Image21-Turbo-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ixim/Image21-Turbo-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-Turbo-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/summary.json from ixim/Image21-Turbo-INT8: direct link, hf CLI and curl.
- Browser
- Download file 350 Bytes
-
https://huggingface.co/ixim/Image21-Turbo-INT8/resolve/main/evaluation/summary.json
- Command line
-
hf download hf://ixim/Image21-Turbo-INT8/evaluation/summary.json
-
curl -L -o summary.json https://huggingface.co/ixim/Image21-Turbo-INT8/resolve/main/evaluation/summary.json
350 Bytes
| { | |
| "pairs": 18, | |
| "cases": 9, | |
| "bf16_mean_seconds": 11.47293396111248, | |
| "int8_mean_seconds": 8.240385450000758, | |
| "bf16_max_allocated_gib": 19.085881233215332, | |
| "int8_max_allocated_gib": 12.622604370117188, | |
| "width": 1024, | |
| "height": 1024, | |
| "steps": 8, | |
| "warmup": true, | |
| "bf16_weight_bytes": 32440133648, | |
| "int8_weight_bytes": 18526523500 | |
| } |