Woohoo new version of @huggingface PEFT just dropped! 😀 Here's why you want it (this is a 13B model):
TOOLS
-
Building open-source server rigs: construction and assembly tutorials
By
–
How did you go about building this? – Are there tutorials online that explain how to put it together? I've built lots of regular boxed servers and workstations, but I feel like these open rigs require some different approaches…
-
AI Tool for VJing with Beatmatching Capabilities
By
–
Would make a great vj’ing tool if it could beatmatch
-
SDXL Refiner Settings and Configuration Guide
By
–
Yep, using the SDXL refiner – here are all the settings: https://
replicate.com/p/7xhk3rtbknhl
kask5xxjmme2ou
… -
EverArt AI Launches Consistent Characters Feature for Creators
By
–
Consistent Characters now in @everartai
— Linus ✦ Ekenstam (@LinusEkenstam) 3 novembre 2023
So powerful 🙌🏻
Excited to see what I can do with it https://t.co/IdZMWHXQUvConsistent Characters now in @everartai So powerful Excited to see what I can do with it
-
VideoReTalking Model Achieves Impressive Lip-Sync Quality
By
–
I'm blown away by the lip-sync quality of the VideoReTalking model.
— fofr (@fofrAI) 3 novembre 2023
– created an image with my SDXL fine-tune
– passed img to @runwayml Gen2 to animate
– used video and VideoReTalking model to lip-sync:https://t.co/MAzbb5Beujhttps://t.co/TXK40Ck4Qf https://t.co/bQdy46DtVd pic.twitter.com/h1T0OpcTKsI'm blown away by the lip-sync quality of the VideoReTalking model. – created an image with my SDXL fine-tune
– passed img to @runwayml Gen2 to animate
– used video and VideoReTalking model to lip-sync: https://
replicate.com/cjwbw/video-re
talking
… https://
replicate.com/p/ql7ay5lbno2i
s3no2wpwvzsrna
… -
LangChain Newsletter: Templates, Data Annotation, and Weekly Insights
By
–
Latest LangChain Newsletter is out LangChain Templates resources + favorites
Data Annotation Queue resources in Favorite Blogs from the week
…and more! read here or sign up to get it in your inbox every other week https://
blog.langchain.dev/week-of-10-30-
langchain-release-notes/
… -
Embedding Cache Feature Released for LLM Responses
By
–
💾 Embedding Cache
— FlowiseAI (@FlowiseAI) 3 novembre 2023
We released cache for LLM response in the last release, now we bring it to embeddings!
Embeddings can now be cached to prevent the need for recomputation, saving you additional💰 pic.twitter.com/EIxeCCeP5gEmbedding Cache We released cache for LLM response in the last release, now we bring it to embeddings! Embeddings can now be cached to prevent the need for recomputation, saving you additional
-
SearchAPI: Real-Time SERP API for Web Data Extraction
By
–
SearchAPI @searchapi_io is a real-time SERP API solution for seamless web data extratction. Available now as a document loader and tool on Flowise!
-
UnstructuredIO Enables RAG Pipelines Multiple File Types Flowise
By
–
📂 Unstructured@UnstructuredIO is the key element when building a RAG pipeline with different file types, supporting pptx, html, png and many more.
— FlowiseAI (@FlowiseAI) 3 novembre 2023
Now available on Flowise, excited to see what people can build with it! pic.twitter.com/xrFNL7rNq2Unstructured @UnstructuredIO is the key element when building a RAG pipeline with different file types, supporting pptx, html, png and many more. Now available on Flowise, excited to see what people can build with it!