Ana içeriğe geç

VisualCloze

Model Source Revision Weight license Parity (CPU, fp32)
visualcloze-384 (+ image input) VisualCloze/VisualClozePipeline-384 59c469d Apache-2.0 Verified

Models: visualcloze-384 · Task: t2i

VisualCloze generates the missing images in the final row of a visual in-context grid. Earlier rows are complete examples; the final row supplies one or more condition images and uses None for every target to generate. Results are returned left to right for those None entries.

from imagehub import pipeline

grid = [
    [example_input, example_output],
    [query_input, None],
]

with pipeline("t2i", backend="visualcloze-384", model="checkpoints/visualcloze-384") as pipe:
    result = pipe(
        "Each row shows a process ...",
        image=grid,
        content_prompt=None,
        seed=0,
    )
  • Input. image is required. Every row has the same number of images, no earlier row may contain None, and the final row must have at least one. content_prompt optionally captions the target. The default settings are 30 steps, guidance 30.0, 512 text tokens and upsampling strength 0.3. height, width, negative prompts and batching options are unsupported.
  • Resolution. The grid-generation stage resizes each row around 384 pixels. Its targets are then passed as uint8 images to a FLUX Fill upsampling stage. Set both upsampling_height and upsampling_width, or neither; the default uses the first supplied image in the final row, caps it at 1024² pixels and rounds down to multiples of 16. Set upsampling_strength=0 to return the generation-stage targets directly.
  • Deliberate compatibility differences. imagehub uses the authors' plain layout instruction rather than the tuple representation emitted by diffusers, and keeps each target's native aspect during multi-target preprocessing rather than applying diffusers' swapped resize arguments.
  • License. The published weights are Apache-2.0, but they are built on FLUX.1-Fill-dev, whose own license is non-commercial. Check the applicable terms before use.