---
license: mit
base_model:
  - black-forest-labs/FLUX.2-klein-4B
  - openbmb/MiniCPM5-1B
  - black-forest-labs/FLUX.2-small-decoder
tags:
  - flux
  - flux2
  - distillation
  - lora
  - text-to-image
  - diffusers
library_name: diffusers
pipeline_tag: text-to-image
---

# flux2tiny — Distilled FLUX.2-klein-4B with MiniCPM5-1B Text Encoder

This repository contains the **trained adapter and LoRA weights** for flux2tiny,
a distilled version of [FLUX.2-klein-4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B)
that replaces the 4B-parameter Qwen3-4B text encoder with
[MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) (1.08B parameters).

## What's in this repo

| File | Size | Description |
|:-----|:-----|:------------|
| `adapter.safetensors` | ~23 MB | Projection adapter (3× Linear 1536→2560, concatenated to 7680) |
| `transformer_lora/adapter_model.safetensors` | ~7.5 MB | PEFT LoRA weights (rank 16) for Flux2Transformer2DModel |
| `transformer_lora/adapter_config.json` | ~1 KB | PEFT LoRA configuration |

## Required base models (downloaded automatically)

- [black-forest-labs/FLUX.2-klein-4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B) — Transformer backbone
- [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) — Student text encoder
- [black-forest-labs/FLUX.2-small-decoder](https://huggingface.co/black-forest-labs/FLUX.2-small-decoder) — VAE decoder

## Usage

```python
# Clone the code repo
# git clone https://github.com/ElMiloPy/flux2tiny.git

from pipeline import Flux2TinyPipeline

pipe = Flux2TinyPipeline(
    adapter_path="path/to/adapter.safetensors",
    lora_path="path/to/transformer_lora",
)

image = pipe("A cat sitting on a windowsill at sunset", height=512, width=512)
image.save("output.png")
```

Or via CLI:
```bash
python generate.py "A cat sitting on a windowsill at sunset" \
    --adapter path/to/adapter.safetensors \
    --lora path/to/transformer_lora \
    --size 512x512
```

## Training details

Trained via a 3-stage knowledge distillation pipeline:

1. **Adapter pre-training** — MSE alignment between MiniCPM5-1B and Qwen3-4B hidden states
2. **Teacher latent generation** — 15,000 latent-prompt pairs from the original FLUX.2 pipeline
3. **Flow Matching LoRA distillation** — Joint training of adapter + transformer LoRA on teacher latents

See [github.com/ElMiloPy/flux2tiny](https://github.com/ElMiloPy/flux2tiny) for full details.

## License

- **These weights**: MIT
- **FLUX.2-klein-4B**: Apache 2.0
- **MiniCPM5-1B**: Apache 2.0