Instructions to use litert-community/Z-Image-Turbo-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use litert-community/Z-Image-Turbo-LiteRT with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
README: clean hero + honest on-device output note
Browse files
README.md
CHANGED
|
@@ -17,11 +17,15 @@ Alibaba Tongyi-MAI **[Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-T
|
|
| 17 |
(6B, Apache-2.0) — a Single-Stream Diffusion Transformer (S3-DiT) — converted to
|
| 18 |
**LiteRT `CompiledModel`** int8 graphs that generate an image fully on the phone GPU.
|
| 19 |
|
| 20 |
-

|
| 21 |
|
| 22 |
+
Prompt: *"a red apple on a wooden table, studio lighting"* (256 px, 8 steps). First 6B
|
| 23 |
+
diffusion generator verified producing a real image on a commodity 8 GB phone (Pixel 8a
|
| 24 |
+
Mali GPU), via chunked sequential residency.
|
| 25 |
+
|
| 26 |
+
<img src="pixel8a_generated.png" width="224"><br>
|
| 27 |
+
*Actual on-device output (Pixel 8a Mali GPU, int8) — reproduces the reference at corr 0.966
|
| 28 |
+
(a faint per-patch texture from int8 quantization).*
|
| 29 |
|
| 30 |
## Graphs in this repo
|
| 31 |
|