Instructions to use sridevshenoy/urmila with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sridevshenoy/urmila 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.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("sridevshenoy/urmila")

prompt = "UNICODE\u0000\u0000l\u0000o\u0000n\u0000g\u0000 \u0000s\u0000h\u0000o\u0000t\u0000 \u0000s\u0000c\u0000e\u0000n\u0000i\u0000c\u0000 \u0000p\u0000r\u0000o\u0000f\u0000e\u0000s\u0000s\u0000i\u0000o\u0000n\u0000a\u0000l\u0000 \u0000p\u0000h\u0000o\u0000t\u0000o\u0000g\u0000r\u0000a\u0000p\u0000h\u0000 \u0000o\u0000f\u0000 \u0000b\u0000o\u0000r\u0000s\u0000e\u0000 \u0000s\u0000i\u0000t\u0000t\u0000i\u0000n\u0000g\u0000 \u0000o\u0000n\u0000 \u0000b\u0000e\u0000d\u0000 \u0000,\u0000 \u0000w\u0000e\u0000a\u0000r\u0000i\u0000n\u0000g\u0000 \u0000r\u0000e\u0000d\u0000 \u0000s\u0000a\u0000r\u0000e\u0000e\u0000 \u0000l\u0000a\u0000u\u0000g\u0000h\u0000i\u0000n\u0000g\u0000,\u0000 \u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000b\u0000h\u0000a\u0000g\u0000y\u0000a\u0000s\u0000h\u0000r\u0000i\u0000-\u0000b\u0000o\u0000r\u0000s\u0000e\u0000-\u00000\u00000\u00000\u00000\u00000\u00008\u0000:\u00001\u0000>\u0000 \u0000,\u0000 \u0000p\u0000e\u0000r\u0000f\u0000e\u0000c\u0000t\u0000 \u0000v\u0000i\u0000e\u0000w\u0000p\u0000o\u0000i\u0000n\u0000t\u0000,\u0000 \u0000h\u0000i\u0000g\u0000h\u0000l\u0000y\u0000 \u0000d\u0000e\u0000t\u0000a\u0000i\u0000l\u0000e\u0000d\u0000,\u0000 \u0000w\u0000i\u0000d\u0000e\u0000-\u0000a\u0000n\u0000g\u0000l\u0000e\u0000 \u0000l\u0000e\u0000n\u0000s\u0000,\u0000 \u0000h\u0000y\u0000p\u0000e\u0000r\u0000 \u0000r\u0000e\u0000a\u0000l\u0000i\u0000s\u0000t\u0000i\u0000c\u0000,\u0000 \u0000w\u0000i\u0000t\u0000h\u0000 \u0000d\u0000r\u0000a\u0000m\u0000a\u0000t\u0000i\u0000c\u0000 \u0000s\u0000k\u0000y\u0000,\u0000 \u0000p\u0000o\u0000l\u0000a\u0000r\u0000i\u0000z\u0000i\u0000n\u0000g\u0000 \u0000f\u0000i\u0000l\u0000t\u0000e\u0000r\u0000,\u0000 \u0000n\u0000a\u0000t\u0000u\u0000r\u0000a\u0000l\u0000 \u0000l\u0000i\u0000g\u0000h\u0000t\u0000i\u0000n\u0000g\u0000,\u0000 \u0000v\u0000i\u0000v\u0000i\u0000d\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000s\u0000,\u0000 \u0000e\u0000v\u0000e\u0000r\u0000y\u0000t\u0000h\u0000i\u0000n\u0000g\u0000 \u0000i\u0000n\u0000 \u0000s\u0000h\u0000a\u0000r\u0000p\u0000 \u0000f\u0000o\u0000c\u0000u\u0000s\u0000,\u0000 \u0000H\u0000D\u0000R\u0000,\u0000 \u0000U\u0000H\u0000D\u0000,\u0000 \u00006\u00004\u0000K\u0000"
image = pipe(prompt).images[0]

Inference
Notebooks
Google Colab
Kaggle
Local Apps
Draw Things
DiffusionBee

How to use from the

Use from the

Diffusers library

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.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("sridevshenoy/urmila")

prompt = "UNICODE\u0000\u0000l\u0000o\u0000n\u0000g\u0000 \u0000s\u0000h\u0000o\u0000t\u0000 \u0000s\u0000c\u0000e\u0000n\u0000i\u0000c\u0000 \u0000p\u0000r\u0000o\u0000f\u0000e\u0000s\u0000s\u0000i\u0000o\u0000n\u0000a\u0000l\u0000 \u0000p\u0000h\u0000o\u0000t\u0000o\u0000g\u0000r\u0000a\u0000p\u0000h\u0000 \u0000o\u0000f\u0000 \u0000b\u0000o\u0000r\u0000s\u0000e\u0000 \u0000s\u0000i\u0000t\u0000t\u0000i\u0000n\u0000g\u0000 \u0000o\u0000n\u0000 \u0000b\u0000e\u0000d\u0000 \u0000,\u0000 \u0000w\u0000e\u0000a\u0000r\u0000i\u0000n\u0000g\u0000 \u0000r\u0000e\u0000d\u0000 \u0000s\u0000a\u0000r\u0000e\u0000e\u0000 \u0000l\u0000a\u0000u\u0000g\u0000h\u0000i\u0000n\u0000g\u0000,\u0000 \u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000b\u0000h\u0000a\u0000g\u0000y\u0000a\u0000s\u0000h\u0000r\u0000i\u0000-\u0000b\u0000o\u0000r\u0000s\u0000e\u0000-\u00000\u00000\u00000\u00000\u00000\u00008\u0000:\u00001\u0000>\u0000 \u0000,\u0000 \u0000p\u0000e\u0000r\u0000f\u0000e\u0000c\u0000t\u0000 \u0000v\u0000i\u0000e\u0000w\u0000p\u0000o\u0000i\u0000n\u0000t\u0000,\u0000 \u0000h\u0000i\u0000g\u0000h\u0000l\u0000y\u0000 \u0000d\u0000e\u0000t\u0000a\u0000i\u0000l\u0000e\u0000d\u0000,\u0000 \u0000w\u0000i\u0000d\u0000e\u0000-\u0000a\u0000n\u0000g\u0000l\u0000e\u0000 \u0000l\u0000e\u0000n\u0000s\u0000,\u0000 \u0000h\u0000y\u0000p\u0000e\u0000r\u0000 \u0000r\u0000e\u0000a\u0000l\u0000i\u0000s\u0000t\u0000i\u0000c\u0000,\u0000 \u0000w\u0000i\u0000t\u0000h\u0000 \u0000d\u0000r\u0000a\u0000m\u0000a\u0000t\u0000i\u0000c\u0000 \u0000s\u0000k\u0000y\u0000,\u0000 \u0000p\u0000o\u0000l\u0000a\u0000r\u0000i\u0000z\u0000i\u0000n\u0000g\u0000 \u0000f\u0000i\u0000l\u0000t\u0000e\u0000r\u0000,\u0000 \u0000n\u0000a\u0000t\u0000u\u0000r\u0000a\u0000l\u0000 \u0000l\u0000i\u0000g\u0000h\u0000t\u0000i\u0000n\u0000g\u0000,\u0000 \u0000v\u0000i\u0000v\u0000i\u0000d\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000s\u0000,\u0000 \u0000e\u0000v\u0000e\u0000r\u0000y\u0000t\u0000h\u0000i\u0000n\u0000g\u0000 \u0000i\u0000n\u0000 \u0000s\u0000h\u0000a\u0000r\u0000p\u0000 \u0000f\u0000o\u0000c\u0000u\u0000s\u0000,\u0000 \u0000H\u0000D\u0000R\u0000,\u0000 \u0000U\u0000H\u0000D\u0000,\u0000 \u00006\u00004\u0000K\u0000"
image = pipe(prompt).images[0]

urmila

Prompt

UNICODElong shot scenic professional photograph of borse sitting on bed , wearing red saree laughing, <lora:bhagyashri-borse-000008:1> , perfect viewpoint, highly detailed, wide-angle lens, hyper realistic, with dramatic sky, polarizing filter, natural lighting, vivid colors, everything in sharp focus, HDR, UHD, 64K

Trigger words

You should use borse to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Downloads last month: 4

Model tree for sridevshenoy/urmila

Base model

black-forest-labs/FLUX.1-dev

Adapter

(40369)

this model