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("Fihade/Retro-Collage-Art-Flux-Dev")
prompt = "ff-collage, a girl, portrait"
image = pipe(prompt).images[0]Retro-Collage-Art

- Prompt
- ff-collage, a girl, portrait
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg

- Prompt
- ff-collage, ski, ski resort, winter, snow
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg

- Prompt
- ff-collage, flowers, butterflies, tropical, montage, people, wildlife, foliage, vibrant colors, nature, collage
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg

- Prompt
- ff-collage, woman's face, colorful, abstract shapes, splatter, lips, nose, eyes, looking upward
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg

- Prompt
- ff-collage, young boy, fragmented, mixed media, textured, abstract elements, face, paper pieces, cracks, layered
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg

- Prompt
- ff-collage, a girl is lying on the sofa
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg

- Prompt
- ff-collage, giant butterfly, people looking up, night sky, flowers, moon
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg

- Prompt
- ff-collage, woman, nature, birds, flower, sunglasses, forest reflection, surreal, mixed media, vibrant colors
- Negative Prompt
- score_4, score_5, score_6, low quality, text, blurry, noisy, FastNegativeV2, epiCPhoto-neg
Model description
βRetro collage Artβ LoRA model, I hope it will be easier to make some collage style pictures
Trigger words
You should use ff-collage 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
- 61
Model tree for Fihade/Retro-Collage-Art-Flux-Dev
Base model
black-forest-labs/FLUX.1-dev