import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Veetance/FLUX-Klein-9B-KV-NF4", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]FLUX-Klein-9B-KV-NF4
This repository contains the FLUX Klein 9B KV runtime bundle prepared for the Asset Editor runtime.
Model Details
- Architecture: FLUX Klein 9B KV
- Quantization: NF4
- Primary use: local asset generation for the Asset Editor KV path
- License: personal, non-commercial use only
Included Runtime Components
transformer/tokenizer/vae/scheduler/
Runtime Notes
- This KV bundle intentionally excludes the text encoder.
- The active loader resolves the encoder from the base 9B bundle at
models/klein-9b/text_encoder_9b_nf4. - This repository mirrors the working local KV layout used by the current app path.
Integration
Optimized for the Veetance Asset Editor KV runtime.
Links
- Core engine: Veetance Asset Editor
- Triage and development: Asset Editor GitHub
See LICENSE.txt for the personal-use terms.
- Downloads last month
- -