Instructions to use ahmethamditanpinar/Flux2-Klein-9B-Consistency-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ahmethamditanpinar/Flux2-Klein-9B-Consistency-diffusers 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-9B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ahmethamditanpinar/Flux2-Klein-9B-Consistency-diffusers") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Flux2-Klein-9B-Consistency V2, Diffusers naming
dx8152's consistency LoRA for FLUX.2 [klein] 9B, version 2, from
dx8152/Flux2-Klein-9B-Consistency
(Flux2-Klein-9B-consistency-V2.safetensors, Apache 2.0), with its layer names converted from Black Forest Labs'
layout (diffusion_model.double_blocks...) to Diffusers' (transformer.transformer_blocks...) by Diffusers' own
_convert_non_diffusers_flux2_lora_to_diffusers. The weights are unchanged; the fused query-key-value layers are split
into separate query, key and value layers, as the conversion does. All credit for the LoRA belongs to its author.
- Downloads last month
- 38
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for ahmethamditanpinar/Flux2-Klein-9B-Consistency-diffusers
Base model
black-forest-labs/FLUX.2-klein-9B