Originally posted to <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev">Huggingface</a>.Full <a target="_blank" rel="ugc" href="https://education.civitai.com/quickstart-guide-to-flux-1/#flux-tools">Flux Tools Guide</a>, including example workflows, live now!If you're looking to get started using Flux, <a target="_blank" rel="ugc" href="https://education.civitai.com/quickstart-guide-to-flux-1/">check out our Guide here</a>.<code>FLUX.1 Canny [dev]</code> is 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image. For more information, please read our <a target="_blank" rel="ugc" href="https://blackforestlabs.ai/flux-1-tools/">blog post</a>.<h2 id="key-features-dw8x7y9ek">Key Features</h2><ol><li>Cutting-edge output quality.</li><li>It blends impressive prompt adherence with maintaining the structure of source images based on canny edges.</li><li>Trained using guidance distillation, making <code>FLUX.1 Canny [dev]</code> more efficient.</li><li>Open weights to drive new scientific research, and empower artists to develop innovative workflows.</li><li>Generated outputs can be used for personal, scientific, and commercial purposes as described in the <code>FLUX.1 [dev]</code> Non-Commercial License.</li></ol><h2 id="usage-ykbxuk35f">Usage</h2>We provide a reference implementation of <code>FLUX.1 Canny [dev]</code>, as well as sampling code, in a dedicated <a target="_blank" rel="ugc" href="https://github.com/black-forest-labs/flux">github repository</a>. Developers and creatives looking to build on top of <code>FLUX.1 Canny [dev]</code> are encouraged to use this as a starting point.

Files with SHA256: 996876670169591cb412b937fbd46ea14cbed6933aef17c48a2dcd9685c98cdb