Built with Qwen. Research and evaluation only, non-commercial. This is the rank64 EMA adapter from qwen21-m11-r64/ckpt-3000-ema. It redraws a furniture carcass as an orthographic front elevation: solid black boards and white openings. It is an adapter, not a complete model. It does not infer real width, depth, thickness, hardware, hidden joints or safe construction. GPT Image 2.5: frontal edit → board drawing. m11: photo → board drawing. Both actual drawings are compiled by the same Fabivo reader with no repaired boards. Three saved examples compare these different pipelines, not matched inference budgets or independent unseen accuracy. GPT uses low quality and frontal candidate 1; m11 uses…
Independent publisher
Brandon Gomez
Superpapotas1
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image to image.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.