2 1 6

spooner

spooner2

[email protected]

AI & ML interests

None yet

Recent Activity

new activity about 1 month ago

Kijai/SkyReels-V1-Hunyuan_comfy:Error HyVideoModelLoader

liked a model 3 months ago

hexgrad/Kokoro-82M

upvoted a paper 5 months ago

OmniGen: Unified Image Generation

View all activity

Organizations

None yet

spooner2's activity

New activity in Kijai/SkyReels-V1-Hunyuan_comfy about 1 month ago

Error HyVideoModelLoader

#7 opened about 1 month ago by

Nikita661995

liked a model 3 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 16 days ago • 1.87M • 3.93k

upvoted a paper 5 months ago

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published Sep 17, 2024 • 114

reacted to yongchanghao's post with 🔥 5 months ago

Post

3773

We just released a paper (NeuZip) that compresses VRAM in a lossless manner to run larger models. This should be particularly useful when VRAM is insufficient during training/inference. Specifically, we look inside each floating number and find that the exponents are highly compressible (as shown in the figure below).

Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)

liked a model 8 months ago

alvdansen/flux-koda

Text-to-Image • Updated Aug 16, 2024 • 13k • • 231

New activity in HaileyStorm/FLUX.1-Merges 8 months ago

combined safetensors , but comfyui issue a error.

#3 opened 8 months ago by

demo001s

liked 2 models 8 months ago

black-forest-labs/FLUX.1-dev

Text-to-Image • Updated Aug 16, 2024 • 2.29M • • 9.67k

black-forest-labs/FLUX.1-schnell

Text-to-Image • Updated Aug 16, 2024 • 1.74M • • 3.6k

liked a model 10 months ago

stabilityai/stable-diffusion-3-medium

Text-to-Image • Updated Aug 12, 2024 • 17.6k • • 4.74k

liked a model 11 months ago

ResplendentAI/SOVL_Llama3_8B

Text Generation • Updated Apr 25, 2024 • 747 • 33

reacted to codelion's post with 🚀 11 months ago

Post

1761

Happy to announce the open source framework to turbo charge devops called patchwork - https://github.com/patched-codes/patchwork

You can use it to build patchflows - workflows that use LLMs for software development tasks like bug fixing, pull request review, library migration and documentation.

Supports any LLM of your choice including our own MoE model - patched-codes/patched-mix-4x7B

Give it a try!

2 replies