jc-builds commited on
Commit
994c982
·
verified ·
1 Parent(s): b22ce09

engine renamed: KilnImage → Mirage

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -21,14 +21,14 @@ base_model: baidu/ERNIE-Image-Turbo
21
  # ERNIE-Image-Turbo — iOS bundle
22
 
23
  <p align="center">
24
- <a href="https://github.com/haplollc/KilnImage"><img alt="KilnImage" src="https://img.shields.io/badge/Runs%20on-KilnImage-orange" /></a>
25
  <a href="https://huggingface.co/baidu/ERNIE-Image"><img alt="Upstream" src="https://img.shields.io/badge/Upstream-baidu%2FERNIE--Image-blue" /></a>
26
  <img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-lightgrey" />
27
  <img alt="Params" src="https://img.shields.io/badge/params-8B-purple" />
28
  <img alt="Distill" src="https://img.shields.io/badge/distill-Turbo-green" />
29
  </p>
30
 
31
- A mobile-friendly bundle of **ERNIE-Image-Turbo** — Baidu's 8B single-stream DiT, distilled for fast inference, with state-of-the-art text rendering quality among open-weight models. Bundled with Ministral 3B text encoder + Flux VAE for on-device inference via [**KilnImage**](https://github.com/haplollc/KilnImage).
32
 
33
  ERNIE-Image-Turbo is particularly strong at:
34
  - **Photorealism** at 1024×1024
@@ -45,10 +45,10 @@ ERNIE-Image-Turbo is particularly strong at:
45
 
46
  Total bundle: **~5.9 GB**. Total GPU residency: ~7 GB. **iPhone 16 Pro / 17 Pro / Mac** territory.
47
 
48
- ## Quick start (KilnImage)
49
 
50
  ```swift
51
- import KilnImage
52
 
53
  let docs = FileManager.default.urls(for: .documentDirectory, in: .userDomainMask)[0]
54
 
@@ -79,7 +79,7 @@ If you need **text inside images** that actually renders correctly (signs, label
79
  | Text encoder | [unsloth/Ministral-3-3B-Instruct-2512-GGUF](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF) | Apache 2.0 |
80
  | VAE | [ffxvs/vae-flux](https://huggingface.co/ffxvs/vae-flux) (re-host of FLUX.1's `ae.safetensors`) | FLUX-1-dev-non-commercial |
81
 
82
- ## Performance (KilnImage, rough)
83
 
84
  | Device | 1024² @ 8 steps |
85
  |---|---|
@@ -89,4 +89,4 @@ If you need **text inside images** that actually renders correctly (signs, label
89
 
90
  ## Built by
91
 
92
- [Haplo](https://haplo.app) · [KilnImage on GitHub](https://github.com/haplollc/KilnImage)
 
21
  # ERNIE-Image-Turbo — iOS bundle
22
 
23
  <p align="center">
24
+ <a href="https://github.com/haplollc/Mirage"><img alt="Mirage" src="https://img.shields.io/badge/Runs%20on-Mirage-orange" /></a>
25
  <a href="https://huggingface.co/baidu/ERNIE-Image"><img alt="Upstream" src="https://img.shields.io/badge/Upstream-baidu%2FERNIE--Image-blue" /></a>
26
  <img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-lightgrey" />
27
  <img alt="Params" src="https://img.shields.io/badge/params-8B-purple" />
28
  <img alt="Distill" src="https://img.shields.io/badge/distill-Turbo-green" />
29
  </p>
30
 
31
+ A mobile-friendly bundle of **ERNIE-Image-Turbo** — Baidu's 8B single-stream DiT, distilled for fast inference, with state-of-the-art text rendering quality among open-weight models. Bundled with Ministral 3B text encoder + Flux VAE for on-device inference via [**Mirage**](https://github.com/haplollc/Mirage).
32
 
33
  ERNIE-Image-Turbo is particularly strong at:
34
  - **Photorealism** at 1024×1024
 
45
 
46
  Total bundle: **~5.9 GB**. Total GPU residency: ~7 GB. **iPhone 16 Pro / 17 Pro / Mac** territory.
47
 
48
+ ## Quick start (Mirage)
49
 
50
  ```swift
51
+ import Mirage
52
 
53
  let docs = FileManager.default.urls(for: .documentDirectory, in: .userDomainMask)[0]
54
 
 
79
  | Text encoder | [unsloth/Ministral-3-3B-Instruct-2512-GGUF](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF) | Apache 2.0 |
80
  | VAE | [ffxvs/vae-flux](https://huggingface.co/ffxvs/vae-flux) (re-host of FLUX.1's `ae.safetensors`) | FLUX-1-dev-non-commercial |
81
 
82
+ ## Performance (Mirage, rough)
83
 
84
  | Device | 1024² @ 8 steps |
85
  |---|---|
 
89
 
90
  ## Built by
91
 
92
+ [Haplo](https://haplo.app) · [Mirage on GitHub](https://github.com/haplollc/Mirage)