import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("wikeeyang/Flux2-Klein-9B-True-V2", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("B4100/instapics")
prompt = "Trigger Word: instapic, hard flash, camera flash, smartphone photo, candid, shot on iphone, high detail skin Recommended Strength: 0.8 to 1.2 (Start at 1.0. Lower for a cleaner look, higher for more \"raw\" camera grit). Target Models: Optimized for Zeetrait (ZIT) and Flux 2 Klein. Prompts: Works great with keywords like “selfie,” “mirror selfie,” “flash photography,” “candid,” “phone camera.”"
image = pipe(prompt).images[0]instapic
- Prompt
- Trigger Word: instapic, hard flash, camera flash, smartphone photo, candid, shot on iphone, high detail skin Recommended Strength: 0.8 to 1.2 (Start at 1.0. Lower for a cleaner look, higher for more "raw" camera grit). Target Models: Optimized for Zeetrait (ZIT) and Flux 2 Klein. Prompts: Works great with keywords like “selfie,” “mirror selfie,” “flash photography,” “candid,” “phone camera.”
Trigger words
You should use instapic to trigger the image generation.
You should use detailed skin to trigger the image generation.
You should use capture from phone to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 20
Model tree for B4100/instapics
Base model
black-forest-labs/FLUX.2-klein-9B Finetuned
wikeeyang/Flux2-Klein-9B-True-V2