Instructions to use hellorob/uf0d0w-flux2klein9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hellorob/uf0d0w-flux2klein9b with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-base-9B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("hellorob/uf0d0w-flux2klein9b") prompt = "uf0d0w" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
uf0d0w β FLUX.2 Klein 9B LoRA
A **lora trained on still frames from the DOW UAP documents ** LoRA trained on top of FLUX.2-klein-base-9B.
Based on the FLUX.2-klein-base-9B foundation model.
Model Files
uf0d0w-v2_flux2klein9b.safetensors
Model Details
- Base Model: FLUX.2-klein-base-9B
- Training Type: LoRA (rank 32)
- Trigger Word:
uf0d0w
Prompt Template
uf0d0w, teal crosshairs, black and white surveillance photo, {prompt}, sensor noise, degraded quality
Replace {prompt} with the subject of your scene. The wrapping text reinforces the LoRA's visual signature β the trigger alone will fire the style, but the full template anchors the surveillance look much more consistently.
Examples:
uf0d0w, teal crosshairs, black and white surveillance photo, a metallic disc hovering over a desert highway, sensor noise, degraded quality
uf0d0w, teal crosshairs, black and white surveillance photo, a glowing orb above a residential street at night, sensor noise, degraded quality
uf0d0w, teal crosshairs, black and white surveillance photo, a tic-tac shaped object banking over the open Pacific, sensor noise, degraded quality
π Using in ComfyUI
- Copy
uf0d0w-v2_flux2klein9b.safetensorsintomodels/loras/(aflux2-klein/subfolder is a nice convention if you have multiple Klein LoRAs). - Use any FLUX.2 Klein 9B workflow as your base.
- Add a
Load LoRAnode between the model loader and the sampler β set strength somewhere between 0.8 and 1.2 to start. - Build prompts from the prompt template above.
License
This LoRA is a derivative of FLUX.2-klein-base-9B and inherits its non-commercial license terms. See the FLUX.2 Klein license for the full text.
- Downloads last month
- 4
Model tree for hellorob/uf0d0w-flux2klein9b
Base model
black-forest-labs/FLUX.2-klein-base-9B