BigLove Klein Collection
Support Notice
I pay for these models out of my own pocket and share them here so people can access them freely. Please understand that this repository is provided as-is. I’m not able to provide individual support, troubleshooting, custom instructions, or answer repeated questions for every upload.
Feel free to download and use the files, but please don’t expect active maintenance or personal support.
Available Files
| File | Format | Size | Use Case |
|---|---|---|---|
bigLove_klein4_mxfp8.safetensors | mxfp8 | ~9 GB | 8-bit, smaller file |
BigLoveKlein4_nf4.safetensors | nv4 | ~5 GB | 4-bit normalized (pruned) |
bigLoveKlein4_nvfp4.safetensors | nvfp4 | ~5 GB | 4-bit normalized |
bigLove_klein4_Q5_K_M.gguf | GGUF | ~6 GB | 5-bit GGUF, balanced (pruned) |
bigLove_klein4_int8_convrot.safetensors | int8 | ~9 GB | 8-bit, smaller file |
bigLoveKlein4_fp8mixed.safetensors | fp8 | ~9 GB | 8-bit, smaller file (pruned) |
bigLove_klein4_bf16.safetensors | BF16 | ~18 GB | BF16, good balance (pruned) |
bigLove_klein3_Q5_K_M.gguf | GGUF | 6 GB | v.3 |
bigLove_klein3.safetensors | BF16 | 18 GB | v.3 |
bigLove_klein3_fp8.safetensors | FP8 | 9 GB | v.3 |
klein-biglove-v2.1.safetensors | sft | na | na |
bigLove_klein2_Bf16.safetensors | BF16 | ~18 GB | Full precision, best quality |
bigLove_klein2_bf16_pruned.safetensors | BF16 (pruned) | ~18 GB | Pruned weights, slightly faster |
bigLove_klein2_fp8_pruned.safetensors | FP8 (pruned) | ~9 GB | Good balance of quality & VRAM |
bigLove_klein2_nf4.safetensors | NF4 | ~5 GB | Low VRAM, fast inference |
bigLove_klein2.gguf | GGUF | varies | For GGUF-compatible loaders |
bigLove_klein1_fp8.safetensors | FP8 | ~9 GB | First version, FP8 quantized |
Usage
ComfyUI
Place the desired model file in your ComfyUI/models/diffusion_models/ (or unet) folder and select it in the appropriate loader node.
Diffusers
from diffusers import FluxPipeline
import torch
pipe = FluxPipeline.from_pretrained(
"Granddyser/biglove-klein2-fp8",
torch_dtype=torch.bfloat16
)
pipe.to("cuda")
image = pipe(
prompt="your prompt here",
num_inference_steps=4,
guidance_scale=0.0,
).images[0]
image.save("output.png")
Acknowledgments
Special thanks to SubtleShader for the motivation.
License
FLUX.2-klein-base-9B is licensed by Black Forest Labs. Inc. under the FLUX.2-klein-base-9B Non-Commercial License. Copyright Black Forest Labs. Inc.