FLUX
Collection
1 item • Updated
How to use Rin247/flux-3-image-klein with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Rin247/flux-3-image-klein", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Quantised media packages of black-forest-labs/flux-3-image-klein.
MECHA — Model Engineering & Contextual Hearth Assembly
These media packages have been forged and optimized in the MECHA Forge. Each one holds the Denoiser, Text Encoder, and VAE components packaged together for easier deployment.
| Quant | Denoiser | Text encoder | VAE |
|---|---|---|---|
| FP8 | FP8 | FP8 | FP8 |
| INT8 | INT8 | INT8 | INT8 |
| FP4 | FP4 | FP8 | FP8 |
| INT4 | INT4 | INT8 | INT8 |
The text encoder and VAE are shared between formats: FP4 reuses the FP8 files, INT4 reuses the INT8 files.
text_encoder/qwen3vl_4b_fp8.safetensors (FP8 and FP4)
text_encoder/qwen3vl_4b_int8.safetensors (INT8 and INT4)
transformer/flux_3_image_klein_fp4.safetensors
transformer/flux_3_image_klein_fp8.safetensors
transformer/flux_3_image_klein_int4.safetensors
transformer/flux_3_image_klein_int8.safetensors
vae/flux_3_image_klein_vae_fp8.safetensors (FP8 and FP4)
vae/flux_3_image_klein_vae_int8.safetensors (INT8 and INT4)