Text-to-Audio Generation with Latent Diffusion Models - Speech Research.
Directory
Search results
Published directory entries matching your search.
Balabolka is a text-to-speech application (freeware).
Collection of Jewish texts in Hebrew.
Optimized Stable Diffusion modified to run on lower GPU VRAM.
Beginner's Guide is a text reference page with notes, links, warnings, or organized update details.
BGGenerator helps create memes, fake posts, text boxes, profile images, or playful visual generators.
Disroot pastebin for sharing text snippets through a simple privacy-friendly web interface.
Biodiversity Heritage Library helps find books, reading material, archives, or public-domain educational texts.
Discover amazing ML apps made by the community.
BreakYourOwnNews helps create memes, fake posts, text boxes, profile images, or playful visual generators.
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Collection of stable diffusion webui colab for different checkpoints.
Open-source project that applies AI to workplace tasks, meetings, sales, marketing, or productivity.
caught with malware is a text reference page with notes, links, warnings, or organized update details.
Research data portal for exploring humanities records, including dataset.
Text-to-speech solutions with character.
CET is a text guide, note, or pasted reference with organized instructions or resource links.
Character Design References helps find books, reading material, archives, or public-domain educational texts.
ChordBook helps find books, reading material, archives, or public-domain educational texts.
Turn simple shots into photoshoot-quality images. Realistic lifestyle scenes, on-model photos, clean cutouts. Detail-first results.
Research data portal for exploring humanities records, including text.
Dataset repository covering humanities, with searchable text.
Dataset repository covering humanities, with searchable text.
A CLIP primer with 3500+ prompt output examples.