KilnImage 0.1.0: initial ERNIE-Image-Turbo iOS bundle

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Ministral-3-3B-Instruct-2512-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ernie-image-turbo-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Ministral-3-3B-Instruct-2512-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd46fc371ff0509bfa8657ac956b7de8534d7d9baaa4947975c0648c3aa397f4
+size 2146497824

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+language: en
+pipeline_tag: text-to-image
+tags:
+  - text-to-image
+  - diffusion
+  - ernie
+  - ernie-image
+  - dit
+  - turbo
+  - gguf
+  - quantized
+  - on-device
+  - ios
+  - mobile
+  - apple-silicon
+base_model: baidu/ERNIE-Image-Turbo
+---
+
+# ERNIE-Image-Turbo — iOS bundle
+
+<p align="center">
+  <a href="https://github.com/haplollc/KilnImage"><img alt="KilnImage" src="https://img.shields.io/badge/Runs%20on-KilnImage-orange" /></a>
+  <a href="https://huggingface.co/baidu/ERNIE-Image"><img alt="Upstream" src="https://img.shields.io/badge/Upstream-baidu%2FERNIE--Image-blue" /></a>
+  <img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-lightgrey" />
+  <img alt="Params" src="https://img.shields.io/badge/params-8B-purple" />
+  <img alt="Distill" src="https://img.shields.io/badge/distill-Turbo-green" />
+</p>
+
+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).
+
+ERNIE-Image-Turbo is particularly strong at:
+- **Photorealism** at 1024×1024
+- **Accurate text rendering inside images** — best-in-class among open models
+- **Speed** — distilled to few-step sampling
+
+## What's inside
+
+| File | Role | Size |
+|---|---|---|
+| [`ernie-image-turbo-Q3_K_M.gguf`](./ernie-image-turbo-Q3_K_M.gguf) | Diffusion transformer — 8B params, Q3_K_M | 3.6 GB |
+| [`Ministral-3-3B-Instruct-2512-Q4_K_M.gguf`](./Ministral-3-3B-Instruct-2512-Q4_K_M.gguf) | Text encoder (Mistral3 emits the 3072-dim conditioning tensor ERNIE expects) | 2.0 GB |
+| [`ae.safetensors`](./ae.safetensors) | VAE (from FLUX.1) | 320 MB |
+
+Total bundle: **~5.9 GB**. Total GPU residency: ~7 GB. **iPhone 16 Pro / 17 Pro / Mac** territory.
+
+## Quick start (KilnImage)
+
+```swift
+import KilnImage
+
+let docs = FileManager.default.urls(for: .documentDirectory, in: .userDomainMask)[0]
+
+let engine = try Engine(models: ModelFiles(
+    diffusionModel: docs.appendingPathComponent("ernie-image-turbo-Q3_K_M.gguf"),
+    vae:            docs.appendingPathComponent("ae.safetensors"),
+    textEncoder:    docs.appendingPathComponent("Ministral-3-3B-Instruct-2512-Q4_K_M.gguf")
+))
+
+let image = try await engine.generate(.init(
+    prompt: "a vintage diner sign that reads \"OPEN 24/7\" in red neon, dusk lighting, photorealistic",
+    width: 1024, height: 1024,
+    steps: 8,         // Turbo distillation
+    cfgScale: 1.0     // CFG is baked in
+))
+```
+
+## Why ERNIE-Image-Turbo
+
+If you need **text inside images** that actually renders correctly (signs, labels, captions, UI mocks), this is currently the strongest open-weight option. Mid-2025 evaluations showed ERNIE-Image meeting or beating GPT-Image-1 on text rendering despite being 1/10th the size.
+
+## Provenance
+
+| Component | Upstream | License |
+|---|---|---|
+| Diffusion transformer | [baidu/ERNIE-Image](https://github.com/baidu/ERNIE-Image) | Apache 2.0 |
+| GGUF conversion | [unsloth/ERNIE-Image-Turbo-GGUF](https://huggingface.co/unsloth/ERNIE-Image-Turbo-GGUF) | Apache 2.0 |
+| Text encoder | [unsloth/Ministral-3-3B-Instruct-2512-GGUF](https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF) | Apache 2.0 |
+| VAE | [ffxvs/vae-flux](https://huggingface.co/ffxvs/vae-flux) (re-host of FLUX.1's `ae.safetensors`) | FLUX-1-dev-non-commercial |
+
+## Performance (KilnImage, rough)
+
+| Device | 1024² @ 8 steps |
+|---|---|
+| iPhone 17 Pro | ~3 min |
+| iPhone 16 Pro | ~5 min |
+| M2 / M3 Mac | ~6 min |
+
+## Built by
+
+[Haplo](https://haplo.app) · [KilnImage on GitHub](https://github.com/haplollc/KilnImage)

ae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+size 335304388

ernie-image-turbo-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1813fc1e0e904cc342e7b6791d0165e6dbb6aac30ad2924747b198bc435857
+size 3909632704