Downloads · 30 days
18
33% of all-time downloads
FLUX.2-klein-4B-onnx-int4
hlhc/FLUX.2-klein-4B-onnx-int4
FLUX.2-klein-4B-onnx-int4 is a image-to-image model from hlhc. Use it when you need one image transformed into another. It is set up for onnxruntime. The card lists the license as apache-2.0.
black-forest-labs/FLUX.2-klein-4B exported to ONNX for onnxruntime, with the pipeline's pre- and post-processing folded into the graphs: text encoder MatMulNBits int4 block 128 hqq, transformer MatMulNBits int4 block…
All-time downloads
55
Public
Repo size
15.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data7.5 GB · 95%
At a glance
- Task
- Image-to-Image
- Library
- onnxruntime
- License
- apache-2.0
- Access
- Public
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026
- SHA
- 41667f61
Base models
Model card
From the Hugging Face model README
FLUX.2 [klein] 4B — ONNX (MatMulNBits int4 block 16 hqq)
black-forest-labs/FLUX.2-klein-4B exported to ONNX for onnxruntime, with the pipeline's pre- and post-processing folded
into the graphs: text encoder MatMulNBits int4 block 128 hqq, transformer MatMulNBits int4 block 16 hqq, VAE float32;
activations float32. Same licence as the original (Apache-2.0, LICENSE.md).
| graph | inputs → output |
|---|---|
text_encoder.onnx | input_ids[1,512], attention_mask[1,512] → prompt_embeds[1,512,7680] (Qwen3 hidden states of layers 9/18/27) |
transformer.onnx | hidden_states[1,S,128], encoder_hidden_states[1,512,7680], timestep[1] (= sigma), img_ids[1,S,4], txt_ids[1,512,4] → noise_pred[1,S,128] |
vae_encoder.onnx | image[1,3,H,W] in [-1, 1] → latents[1,128,H/16,W/16] (patchified, batch-norm normalised) |
vae_decoder.onnx | latents[1,128,h,w] → image[1,3,16h,16w] in [-1, 1] |
config.json records the chat-template prefix/suffix, the position-id conventions, the schedule
(flow-match Euler with the empirical mu shift), and the reference-image convention for editing.
MatMulNBits runs on onnxruntime's CPU, CUDA and DirectML providers (not Core ML); zero points: as the quantiser wrote them.
Files
| file | size |
|---|---|
text_encoder.onnx | 0.00 GB |
text_encoder.onnx.data | 3.09 GB |
transformer.onnx | 0.00 GB |
transformer.onnx.data | 4.39 GB |
vae_decoder.onnx | 0.20 GB |
vae_encoder.onnx | 0.14 GB |
Verification (cosine vs the PyTorch modules on identical inputs)
| graph | cosine |
|---|---|
| transformer | 0.95264 |
verification_onnx.png is a 4-step, 512 px text-to-image through onnxruntime; verification_pytorch.png,
when present, the same prompt through diffusers. Exported with scripts/export_klein_onnx.py
(torch 2.14.0+cu130, diffusers 0.40.0, onnxruntime 1.30.0).
- Task
- Image-to-Image
- Library
- onnxruntime
- License
- apache-2.0
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026