Text-to-Image
Diffusers
Safetensors
English
Flux2KleinPipeline
art
stable-diffusion
flux
nf4
asset-editor
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Veetance/FLUX-Klein-4B-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-4B-NF4 | Debloated
This repository contains the FLUX Klein 4B weights, quantized to 4-bit NF4 for the Asset Editor runtime.
Model Details
- Architecture: FLUX.1 Schnell distilled
- Quantization: NF4 (NormalFloat 4-bit)
- Primary use: lightweight asset generation on low-VRAM hardware
- License: Apache-2.0
Integration
Optimized for the Asset Editor Zerodrag pipeline.
Links
- Core engine: Veetance Asset Editor
- Triage and development: Asset Editor GitHub
This is a specialized runtime manifold for the Veetance Asset Editor stack.
- Downloads last month
- 12