| --- |
| license: apache-2.0 |
| base_model: black-forest-labs/FLUX.2-klein-4B |
| base_model_relation: quantized |
| pipeline_tag: text-to-image |
| library_name: coreai |
| tags: |
| - coreai |
| - ios |
| - text-to-image |
| - flux |
| - react-native |
| --- |
| |
| # FLUX.2 klein 4B for Core AI on iPhone |
|
|
| [black-forest-labs/FLUX.2-klein-4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B) (4B parameters, step-distilled text-to-image) exported to Apple Core AI for iOS with the [`apple/coreai-models`](https://github.com/apple/coreai-models) recipe. It runs on iOS 27 and macOS 27 with the `FlowTransformerPipeline` from the `CoreAIDiffusion` product of `coreai-models`, and generates 512x512 images in 4 steps. |
|
|
| ## Files |
|
|
| `ios/` holds the text-to-image components of the recipe's iOS export, 4-bit weights (4.0 GB): |
|
|
| | File | Size | | |
| | --- | --- | --- | |
| | `Transformer_512.aimodel` | 2.0 GB | DiT, 25 blocks, 512x512 | |
| | `TextEncoder.aimodel` | 1.6 GB | Qwen3 text encoder | |
| | `VAEDecoder_half.aimodel` | 95 MB | latent to 512x512 image | |
| | `tokenizer/`, `metadata.json`, `vae_bn_*.npy` | 11 MB | | |
|
|
| The image-to-image transformer and VAE encoder of the full iOS export are left out. The pipeline loads one component at a time by default (`lazyModelLoading`), so it fits in the memory an iPhone 17 Pro gives an app. |
|
|
| ## Use |
|
|
| With [`@react-native-ai/core-ai`](https://github.com/callstackincubator/ai), download the `ios` folder and pass its path: |
|
|
| ```typescript |
| import { coreAI } from '@react-native-ai/core-ai' |
| import { generateImage } from 'ai' |
| |
| const { image } = await generateImage({ |
| model: coreAI.imageModel({ |
| id: 'flux2-klein-4b', |
| source: { type: 'file', uri: fluxModelPath }, |
| }), |
| prompt: 'a red apple on a wooden table', |
| size: '512x512', |
| seed: 42, |
| providerOptions: { 'core-ai': { stepCount: 4 } }, |
| }) |
| ``` |
|
|
| In Swift: |
|
|
| ```swift |
| import CoreAIDiffusionPipeline |
| |
| let pipeline = try await FlowTransformerPipeline(from: modelURL) |
| let configuration = PipelineConfiguration( |
| prompt: "a red apple on a wooden table", |
| seed: 42, |
| stepCount: 4, |
| guidanceScale: 1.0, |
| schedulerType: .discreteFlow |
| ) |
| let image = try await pipeline.generateImages(configuration: configuration) { _ in true }.images[0] |
| ``` |
|
|
| ## Export |
|
|
| From [`apple/coreai-models`](https://github.com/apple/coreai-models) at `5de95c6` (1.0.0), with `coreai-core` 1.0.0b3. This is `--platform iOS` (4-bit, single-function, 512) without the image-to-image components: |
|
|
| ```bash |
| uv run coreai.diffusion.export flux2-klein-4b --single-function \ |
| --components transformer_512 text_encoder vae_decoder_half |
| ``` |
|
|
| ## License |
|
|
| Apache-2.0, as the original model. The weights were converted to Core AI and quantized to 4 bits, and are otherwise unchanged. FLUX.2 [klein] is by [Black Forest Labs](https://bfl.ai). |
|
|
