Downloads · 30 days
181
23% of all-time downloads
prithivMLmods/Flux2-Klein-Cinematic-FlatLog-Control
Flux2-Klein-Cinematic-FlatLog-Control is a image-to-image model from prithivMLmods. Use it when you need one image transformed into another. It is set up for diffusers. The card lists the license as other.
Downloads · 30 days
181
23% of all-time downloads
All-time downloads
775
Public
Repo size
261 MB
Likes
12
Public
Click a slice to open those files.
.safetensors348 MB · 100%
From the Hugging Face model README

Flux2-Klein-Cinematic-FlatLog-Control is an adapter LoRA developed for FLUX.2-klein-base-9B, designed to transform images into a cinematic flat log look. The model reduces contrast and saturation to achieve a neutral, log-style tonal response while preserving the original identity, composition, textures, and geometry. It enables consistent cinematic grading workflows with smooth highlight roll-off, controlled shadows, and artifact-free results.
Compatible with versions 2509 and 2511.
pip install -U diffusers transformers accelerate
import torch
from diffusers import Flux2KleinPipeline
from diffusers.utils import load_image
# Switch to "mps" for Apple devices
pipe = Flux2KleinPipeline.from_pretrained(
"black-forest-labs/FLUX.2-klein-base-9B",
torch_dtype=torch.bfloat16,
device_map="cuda"
)
pipe.load_lora_weights("prithivMLmods/Flux2-Klein-Cinematic-FlatLog-Control")
prompt = "Transform into a cinematic flat log"
input_image = load_image(
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
)
image = pipe(image=input_image, prompt=prompt).images[0]
Trained on ModelScope.cn
Use the following prompt to activate the cinematic flat log behavior:
Transform into a cinematic flat log
You can download the model files from the Files & versions tab: Download