http://wiki.backprop.fr/index.php?action=history&feed=atom&title=Textual_Inversion 2026-05-09T14:20:40Z Historique des versions pour cette page sur le wiki MediaWiki 1.38.4 http://wiki.backprop.fr/index.php?title=Textual_Inversion&diff=22&oldid=prev 2023-01-05T13:35:52Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="fr"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Version précédente</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Version du 5 janvier 2023 à 13:35</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l2">Ligne 2 :</td> <td colspan="2" class="diff-lineno">Ligne 2 :</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>&quot;We learn to generate specific concepts, like personal objects or artistic styles, by describing them using new &quot;words&quot; in the embedding space of pre-trained text-to-image models. These can be used in new sentences, just like any other word.&quot;</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>&quot;We learn to generate specific concepts, like personal objects or artistic styles, by describing them using new &quot;words&quot; in the embedding space of pre-trained text-to-image models. These can be used in new sentences, just like any other word.&quot;</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Textual inversion is a process where you can quickly "teach" a new word to the text model and plain its embeddings close to some visual representation. This is achieved by adding a new token to the vocabulary, freezing the weights of all the models (except the text encoder), and train with a few representative images.</ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr> <!-- diff cache key wikiuser:diff::1.12:old-16:rev-22 --> </table>

Jboscher http://wiki.backprop.fr/index.php?title=Textual_Inversion&diff=16&oldid=prev 2022-12-08T09:29:11Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="fr"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Version précédente</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Version du 8 décembre 2022 à 09:29</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l6">Ligne 6 :</td> <td colspan="2" class="diff-lineno">Ligne 6 :</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Références ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Références ==</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* [https://textual-inversion.github.io]</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* [https://textual-inversion.github.io] <ins style="font-weight: bold; text-decoration: none;">An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion</ins></div></td></tr> <!-- diff cache key wikiuser:diff::1.12:old-15:rev-16 --> </table>

Jboscher http://wiki.backprop.fr/index.php?title=Textual_Inversion&diff=15&oldid=prev 2022-12-08T09:28:49Z

<p>Page créée avec « Textual Inversion est défini de la façon suivante : &quot;We learn to generate specific concepts, like personal objects or artistic styles, by describing them using new &quot;words&quot; in the embedding space of pre-trained text-to-image models. These can be used in new sentences, just like any other word.&quot; == Références == * [https://textual-inversion.github.io] »</p> <p><b>Nouvelle page</b></p><div>Textual Inversion est défini de la façon suivante : <br /> <br /> &quot;We learn to generate specific concepts, like personal objects or artistic styles, by describing them using new &quot;words&quot; in the embedding space of pre-trained text-to-image models. These can be used in new sentences, just like any other word.&quot;<br /> <br /> <br /> == Références ==<br /> <br /> * [https://textual-inversion.github.io]</div>

Jboscher