Instructions to use wikeeyang/Flux2-Klein-9B-True-V3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wikeeyang/Flux2-Klein-9B-True-V3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wikeeyang/Flux2-Klein-9B-True-V3", dtype=torch.bfloat16, device_map="cuda") 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
- DiffusionBee
int4 works on rtx 4070
#8
by ryg81 - opened
int4 works on rtx 4070?
int4 works on rtx 4070?
Yeeeesss! And very fast! I have a 4070 too. (I ve tested it using the custom nodes not native mode)
But why dont use the new fp8 convrot? Is very fast compare than fp8 normal, and works well qith 12 of vram
