import json
import os
import torch
from diffusers import BriaFiboPipeline
from diffusers.modular_pipelines import ModularPipelineBlocks
# -------------------------------
# Load the VLM pipeline
# -------------------------------
torch.set_grad_enabled(False)
# Using Gemini API, requires GOOGLE_API_KEY environment variable
assert os.getenv("GOOGLE_API_KEY") is not None, "GOOGLE_API_KEY environment variable is not set"
vlm_pipe = ModularPipelineBlocks.from_pretrained("briaai/FIBO-gemini-prompt-to-JSON", trust_remote_code=True)
vlm_pipe = vlm_pipe.init_pipeline()
# Using local VLM, uncomment to run
# vlm_pipe = ModularPipelineBlocks.from_pretrained("briaai/FIBO-VLM-prompt-to-JSON", trust_remote_code=True)
# vlm_pipe = vlm_pipe.init_pipeline()
# Load the FIBO pipeline (distilled few-step / DMD-R weights)
pipe = BriaFiboPipeline.from_pretrained(
"briaai/Fibo-1.5",
torch_dtype=torch.bfloat16,
)
pipe.to("cuda")
# pipe.enable_model_cpu_offload() # uncomment if you're getting CUDA OOM errors
# -------------------------------
# Run Prompt to JSON
# -------------------------------
# Create a prompt to generate an initial image
output = vlm_pipe(
prompt="A hyper-detailed, ultra-fluffy owl sitting in the trees at night, looking directly at the camera with wide, adorable, expressive eyes. Its feathers are soft and voluminous, catching the cool moonlight with subtle silver highlights. The owl's gaze is curious and full of charm, giving it a whimsical, storybook-like personality."
)
json_prompt_generate = output.values["json_prompt"]
# -------------------------------
# Run Image Generation
# -------------------------------
# Generate the image from the structured json prompt
results_generate = pipe(
prompt=json_prompt_generate, num_inference_steps=6, guidance_scale=1
)
results_generate.images[0].save("image_generate.png")
with open("image_generate_json_prompt.json", "w") as f:
f.write(json_prompt_generate)
output = vlm_pipe(
json_prompt=json_prompt_generate, prompt="make the owl brown"
)
json_prompt_refine_from_image = output.values["json_prompt"]
results_refine_from_image = pipe(
prompt=json_prompt_refine_from_image, num_inference_steps=6, guidance_scale=1
)
results_refine_from_image.images[0].save("image_refine_from_image.png")
with open("image_refine_from_image_json_prompt.json", "w") as f:
f.write(json_prompt_refine_from_image)
from PIL import Image
original_astronaut_image = Image.open("<path to original astronaut image>")
output = vlm_pipe(
image=original_astronaut_image, prompt="")
json_prompt_inspire = output.values["json_prompt"]
results_inspire = pipe(
prompt=json_prompt_inspire, num_inference_steps=6, guidance_scale=1
)
results_inspire.images[0].save("image_inspire_no_prompt.png")
with open("image_inspire_json_prompt_no_prompt.json", "w") as f:
f.write(json_prompt_inspire)
output = vlm_pipe(
image=original_astronaut_image, prompt="Make futuristic")
json_prompt_inspire = output.values["json_prompt"]
results_inspire = pipe(
prompt=json_prompt_inspire, num_inference_steps=6, guidance_scale=1
)
results_inspire.images[0].save("image_inspire_with_prompt.png")
with open("image_inspire_json_prompt_with_prompt.json", "w") as f:
f.write(json_prompt_inspire)
Citation
We kindly encourage citation of our work if you find it useful.
@article{gutflaish2025generating,
title={Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions},
author={Gutflaish, Eyal and Kachlon, Eliran and Zisman, Hezi and Hacham, Tal and Sarid, Nimrod and Visheratin, Alexander and Huberman, Saar and Davidi, Gal and Bukchin, Guy and Goldberg, Kfir and others},
journal={arXiv preprint arXiv:2511.06876},
year={2025}
}