Saraptah Flux LoRA v1
by obann001
Open source · 5k downloads · 0 likes
0.0
(0 reviews)ImageAPI & LocalAbout
The Saraptah Flux LoRA v1 model is an AI tool specialized in generating images from text, designed to produce creative and detailed visuals. It stands out for its ability to interpret prompts with precision, delivering consistent and aesthetically pleasing results thanks to its optimized training. Ideal for artists, designers, or content creators, it excels in generating a variety of images, from landscapes to fantastical characters. Its activation keyword, "saraptah," allows for easy integration into image generation workflows. This model is distinguished by its flexibility and seamless compatibility with tools like ComfyUI or the Diffusers library.
Documentation
Saraptah
Trained on RTX3060 with ComfyUI:
Trigger words
You should use saraptah to trigger the image generation.
Use it with the 🧨 diffusers library
Py
from diffusers import FluxPipeline
import torch
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload() # ou .to("cuda")
pipe.load_lora_weights('obann001/Saraptah_Flux1.Dev_LoRA_v1', weight_name='model.safetensors'))
prompt = "your prompt"
image = pipe(prompt, num_inference_steps=28, guidance_scale=3.5).images[0]
image.save("output.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
Capabilities & Tags
diffusersfluxlorareplicatedark-skinnxonxiportugalReal Personarttext-to-image
Links & Resources