Feature Extraction
Transformers
Safetensors
Diffusers
English
qwen3
flux
text-encoder
pruning
distillation
Instructions to use SearchingMan/FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SearchingMan/FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="SearchingMan/FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("SearchingMan/FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B") model = AutoModel.from_pretrained("SearchingMan/FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B") - Diffusers
How to use SearchingMan/FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SearchingMan/FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Initial release: pruned 5.1B text encoder for FLUX.2-klein-9B (bitwise-verified export, benchmarks, seed study)
300ccd6 verified | This FLUX Model is licensed by Black Forest Labs Inc. under the FLUX Non-Commercial | |
| License. Copyright Black Forest Labs Inc. IN NO EVENT SHALL BLACK FOREST LABS INC. BE | |
| LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT | |
| OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL. | |
| This repository contains a MODIFIED VERSION (a "Derivative" under the FLUX | |
| Non-Commercial License) of the text encoder component of FLUX.2-klein-9B: | |
| the encoder was structurally pruned (layer removal, layer merging, FFN width pruning, | |
| GQA head-group pruning) and recovery-distilled against the original encoder, | |
| reducing it from 8.19B to 5.10B parameters. The DiT and VAE are NOT included. | |
| This Derivative is not an official product of Black Forest Labs Inc. and has not been | |
| endorsed, approved, or validated by Black Forest Labs Inc. | |