datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
FLUX.2-klein-base-9B_samples_Best_ofThis dataset is a highly diverse set of high quality images generated with FLUX.2 [klein] 9B Base.
NOTE: The Base is not intended for image generation, so do not use these images to judge the quality of the model.
Base is intended for training, as are the samples in this dataset as they can be used for regularization.
Possible uses
Regularization images for training models based on FLUX.2 [klein] 9B Base
Quality testing
Data source
This dataset is derived from… See the full description on the dataset page: https://huggingface.co/datasets/stablellama/FLUX.2-klein-base-9B_samples_Best_of.FLUX.2-klein-base-9B_samplesThis dataset is a highly diverse set of high quality images generated with FLUX.2 [klein] 9B Base.
NOTE: The Base is not intended for image generation, so do not use these images to judge the quality of the model.
Base is intended for training, as are the samples in this dataset as they can be used for regularization.
Possible uses
Regularization images for training models based on FLUX.2 [klein] 9B Base
Quality testing
Data source
The images were created in ComfyUI… See the full description on the dataset page: https://huggingface.co/datasets/stablellama/FLUX.2-klein-base-9B_samples.flux2-klein-latent-trajectories
FLUX.2 Klein Latent Trajectories
This dataset contains synthetic text-to-image generations produced with a local FLUX.2 Klein 4B snapshot, together with the prompts, generated WebP images, and captured intermediate diffusion latent states.
Contents
262,144 generated examples.
512 Torch shard files under shards/, with 512 samples per shard.
One JSON sidecar per shard with generation metadata.
Image resolution: 512 x 512.
Image format: WebP, quality 90.
Diffusion… See the full description on the dataset page: https://huggingface.co/datasets/ryanhlewis/flux2-klein-latent-trajectories.flux-2-klein-9B-schematic-dataset
FLUX.2 Klein Schematic LoRA Dataset
This is the training dataset used for the FLUX.2 Klein Schematic LoRA project.
The LoRA repository is available here:
LoRA: https://huggingface.co/nomadoor/flux-2-klein-9B-schematic-lora
For details about the experiment and dataset construction, see the blog post:
Blog: https://comfyui.nomadoor.net/en/notes/flux2-klein-schematic-lora/
Structure
data/
depth_relative/
input/
target/
caption/
surface_normal/… See the full description on the dataset page: https://huggingface.co/datasets/nomadoor/flux-2-klein-9B-schematic-dataset.flux2-klein-4B-blind-spots
Technical Challenge: Blind Spots of Frontier Models
Model Tested: unsloth/FLUX.2-klein-base-4B-GGUFModality: Text-to-Image (Vision)
How the Model Was Loaded
The model was loaded using a A100 GPU in Google Colab. Because FLUX.2 is a 4B parameter model, I utilized the diffusers library with torch.bfloat16 precision and enabled model CPU offloading to efficiently manage the 15GB VRAM limit during inference.
import torch
from diffusers import Flux2KleinPipeline
device =… See the full description on the dataset page: https://huggingface.co/datasets/itsazza/flux2-klein-4B-blind-spots.
