GitHub repository for
Website for
- Awesome-Diffusion-Personalization: focus on how to efficiently learn a concept/object/style based on large diffusion models
- GroundingDINO: detect everything with text
- OS2D: detect class-image(one shot) in input-image
- Image Deduplicator: detect duplicate image
- SAM(SegmentAnythingModel): cut out any object in any image
- Fast SAM: 50× higher run-time speed than SAM
- Grounded SegmentAnything: detect everything with text and cut object(bounding box, masking)
- CLIP-SAM: detect everything with text and cut object(masking)
- Lang Segment: segment input prompt object
- MaskDINO: auto object detection and segmentation
- SSA(SemanticSegmentAnything): auto object detection and segmentation, label
- Edit Anything:
image edit, edit and generate anything - Stable Diffusion:
text to image, prompt - Dreambooth StableDiffusion:
text to image, fine-tune model with a few examples - Perfusion:
text to image, fine-tune model with a few examples - Dense Diffusion:
text to image, generate image with sketch and prompt - GLIGEN:
text to image, generate image with sketch and prompt - Clip-Interrogator:
image to text, generate prompt - Paint by Example:
image edit, inpaint(input: reference, mask, source image) - Instruct Pix2Pix:
image edit, prompt - Inpaint Anything:
image edit, inpaint(input: prompt) - PAIR Diffusion:
ìmage edit, prompt, image - CycleNet:
image edit, text-guided(winter->summer, horse->zebra etc.)
- open-interpreter: OpenAI's Code Interpreter can run in local
- autodistill: detecting objects with auto-labeled dataset
- Text2Video-Zero:
text to video, prompt - OpenSora:
text to video, prompt
- Bark:
text to audio
- Perplexity AI: answer to any question
- ChatPDF: chat with any PDF
- Elicit: AI research assistant
- DeepL: translator
- Connected Papers: explore connected papers in a visual graph
- Gamma: presentation generator
- LangChain AI: LangChain AI handbook
- DeepLearning.AI: Generative AI short courses