Downloads · 30 days
88
41% of all-time downloads
Z-Image-Turbo-LiteRT-iOS
ladparis/Z-Image-Turbo-LiteRT-iOS
Z-Image-Turbo-LiteRT-iOS is a text-to-image model from ladparis. Use it when you need an image from a text prompt. It is set up for litert. The card lists the license as apache-2.0.
Repackaged from litert-community/Z-Image-Turbo-LiteRT (Apache-2.0, converted from Tongyi-MAI/Z-Image-Turbo) with the host-side tensors required to run the full text-to-image pipeline on device:
All-time downloads
216
Public
Repo size
11.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tflite9.8 GB · 86%
At a glance
- Task
- Text-to-Image
- Library
- litert
- License
- apache-2.0
- Access
- Public
- Created
- Aug 14, 2026
- Updated
- Aug 14, 2026
- SHA
- 4ba9dc8b
Base models
Model card
From the Hugging Face model README
Z-Image-Turbo — LiteRT bundle for Mirage iOS
Repackaged from litert-community/Z-Image-Turbo-LiteRT (Apache-2.0, converted from Tongyi-MAI/Z-Image-Turbo) with the host-side tensors required to run the full text-to-image pipeline on device:
| File | Role |
|---|---|
qwen_enc.tflite | Qwen3-4B text encoder (penultimate hidden state) |
z_embx.tflite / z_refx.tflite | image patch embed + noise refiner |
z_embc.tflite / z_refc.tflite | caption embed + context refiner |
zc_main0..5.tflite | 30 S3-DiT layers, 5 per chunk |
zc_final.tflite | final adaLN + projection |
zvae.tflite | VAE decoder |
host_tensors.safetensors | embed_tokens (fp32), t_embedder MLP, cap_pad_token, x_pad_token |
tokenizer.json | Qwen2 BPE tokenizer |
All graphs are INTEGER-int8, fixed 256×256 output, 64-token prompt budget.
The host loop (RoPE, adaLN timestep embedding, pad masking, x/cap concat,
flow-match Euler, VAE denorm latents / 0.3611 + 0.1159) runs in app code.
License: Apache-2.0 (inherited from Z-Image-Turbo).
- Task
- Text-to-Image
- Library
- litert
- License
- apache-2.0
- Created
- Aug 14, 2026
- Updated
- Aug 14, 2026