GeorgeQi/Color-Palette-Flux_dev

Color-Patette-Flux_dev

Text to Image

Prompt

an intricately designed perfume bottle resting on a vintage carved dressing table, flanked by elegant makeup and jewelry, with a gilded mirror above and a vase of peonies adding a romantic ambiance, all depicted in a refined vintage style.

Prompt

A lively image featuring a bottle of alcopop on a sleek bar counter, a bokeh effect of an enthusiastic crowd and a live band with colorful stage lighting in the background, all wrapped up in a vivid urban nightlife ambiance

Prompt

A luxurious crossbody bag is the centerpiece on a glass shelf, with a selection of high-end accessories neatly arrayed behind it, all bathed in a soft, diffused sunlight that adds a serene and exquisite touch to the image.

Prompt

The table is placed in an outdoor camping scene with a teapot and two teacups on the table, grass, outdoor, sunlight, HD, product photography.

Prompt

A bottle is placed in water, the water covers half of the product, the splash flies, the bottom half of the product placed under the water is clearly visible, waterproof advertising, product advertising, photography, HD, real, 8k

Prompt

A photo of a serene landscape with a calm lake reflecting the surrounding mountains and forests. The mountains have a mix of tree and exposed rock. The sky is overcast, with dark clouds covering the sky. The reflection of the mountains and sky on the lake is mirror-clear. The shoreline is lined with trees. The ground is covered with grass.

import torch
from diffusers import FluxPipeline
  
prompt = "[COLOR_PALETTE] This two-part image showcases the transformation from a color palette to a image. \
          [LEFT] a color palette with five different colors. \
          [RIGHT] an intricately designed perfume bottle resting on a vintage carved dressing table, flanked by elegant makeup and jewelry, with a gilded mirror above and a vase of peonies adding a romantic ambiance, all depicted in a refined vintage style."

pipe_t2i = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
pipe_t2i.load_lora_weights("./color_palette_lora.safetensors")
pipe_t2i.enable_lora()
out = pipe_t2i(prompt=prompt, guidance_scale=3.5, height=768, width=512, num_inference_steps=50).images[0]
out.save("t2i_color_palette.png")

Conditional Generation

import torch
import numpy as np
from PIL import Image
from diffusers.utils import load_image
from diffusers import FluxInpaintPipeline

prompt = "[COLOR_PALETTE] This two-part image showcases the transformation from a color palette to a image. \
          [LEFT] a color palette with five different colors. \
          [RIGHT] an intricately designed perfume bottle resting on a vintage carved dressing table, flanked by elegant makeup and jewelry, with a gilded mirror above and a vase of peonies adding a romantic ambiance, all depicted in a refined vintage style."

pipe_inpainting = FluxInpaintPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
pipe_inpainting.load_lora_weights("./color_palette_lora.safetensors")
mask = load_image("./mask.jpg").resize(size=(768, 512))
color_palette = load_image("./blue.png")
input_image = Image.new('RGB', (768, 512))
input_image.paste(color_palette.resize(size=(256, 512)), (0, 256))
input_image.paste(color_palette.resize(size=(512, 512)), (512, 256))
out = pipe_inpainting(prompt=prompt, image=color_palette, mask_image=mask, guidance_scale=3.5, height=768, width=512, num_inference_steps=50, max_sequence_length=256, strength=1).images[0]
out.save("conda_color_palette.png")

Model description

The model follows the idea of IC-Lora, image splicing is used for training and inferencing. The IC-Lora prompt template is like this👇

[COLOR_PALETTE] This two-part image showcases the transformation from a color palette to a image. [LEFT] a color palette with five different colors.  [RIGHT] xxxxx

Training

Training was done using https://github.com/XLabs-AI/x-flux