That is essentially what it does, but it also uses a 1.45gb tile model to help it do that. https://
huggingface.co/lllyasviel/con
trol_v11f1e_sd15_tile
…
OPEN SOURCE
-
1.45GB Tile Model Enhances Stable Diffusion Image Generation
By
–
-
ControlNet Tile Only Available for SD1.5 Currently
By
–
I think Controlnet tile is only available for SD1.5, no one has trained an SDXL version yet.
-
RealisticVision XL V3 Multi-ControlNet LoRA Model Released
By
–
I've added a RealisticVision XL V3 model to Replicate with multi-controlnet and lora support: https://
replicate.com/fofr/realvisxl
-v3-multi-controlnet-lora
… Outputs also work great when upscaled with something like Magnific. -
i2vgen-xl video generation model speeds up significantly
By
–
i2vgen-xl is now running faster – @chenxi_jw has done some great work to speed it up. Steps are now also exposed.
— fofr (@fofrAI) 5 janvier 2024
16 frame gen:
50 steps down from ~180s to ~115s
25 steps at ~60s
More steps makes more consistency.https://t.co/CH1PsbwTyK https://t.co/Dgl6FfdYmU pic.twitter.com/ZgAP1Yhj10i2vgen-xl is now running faster – @chenxi_jw has done some great work to speed it up. Steps are now also exposed. 16 frame gen:
50 steps down from ~180s to ~115s
25 steps at ~60s More steps makes more consistency. https://
replicate.com/cjwbw/i2vgen-xl -
Groq’s Chat Platform Achieves 300 Tokens Per Second with Llama2
By
–
…and that open-source list means you could learn about the samely named model but on different platforms, yet it will perform differently. This is challenging for providers also. http://
Chat.Groq.com is the fastest for Llama2, 70B at ~300 tokens per second per user but that -
Groq LPU Engine: Kernel-free Llama 2 70B Inference Performance
By
–
Kernel-free, no Cuda, Compiler-only solution.
The current implementation, running on our LPU Inference Engine uses our own processor. The model is Llama 2, 70B 4k sequence at FP16…We haven't even hit the next gear through those other methods. Plenty in the tank left! -
OpenAI Custom RAG with LangChain: Chat with Videos
By
–
Building an OpenAI Custom RAG with LangChain: The Ultimate Tutorial to Chat with your Videos! Awesome tutorial by @austinbv on how to use Whisper + OpenAI + LangChain to talk to your videos Shows off transcription, LCEL, streaming
-
Image Classification with Global Context Vision Transformer Tutorial
By
–
New tutorial on http://
keras.io: Image classification using Global Context Vision Transformer. Works with JAX/TF/PyTorch. -
JAX Framework: Transform Your ML Development Expectations
By
–
Anyway, if you haven't explored JAX yet, you really should. It makes you completely change your expectations for ML frameworks 🙂
-
Keras 3 with JAX Significantly Faster Than PyTorch
By
–
It is not uncommon for Keras 3 + JAX to be 3-5x faster than PyTorch models pulled from research repos on GitHub or from Hugging Face. Though the typical figure is more like 30% faster.