POV:Frank (d/acc) 🎩 πŸ’œ pfp

POV:Frank (d/acc) 🎩 πŸ’œ

@scalinglaw.eth

441 Following
260 Followers
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Looking forward to testing Nous Research forge to compare with gpt-o1. πŸ‘€πŸ‘€πŸ‘€
0 reply
0 recast
2 reactions
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
legend flag!
1 reply
0 recast
1 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
I've joined get hyped waitlist! Join through the frame below and help me climb up the leaderboard! Powered by /beearly 🐝
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
We will deploy this model soon!
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Minted Doodles Certified Viral: Feline Hungry
0 reply
0 recast
0 reaction
m4rsh pfp
m4rsh
@m4rsh
mfer dot com
1 reply
2 recasts
9 reactions
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Cooking flux models on Heurist. Will put link here. πŸ‘‰πŸ˜Ž
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
πŸ™ŒπŸ™ŒπŸ™Œ
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
10 Moxie Passes available β€” mint yours to be eligible for upcoming airdrops, grants, Fan Tokens, and more! cc @betashop.eth @airstack.eth
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Apple will fit many LoRa adapters into devices, with the base models. The vector indexer will have multi-modal capabilities, allowing it to fine-tune texts, images, videos, and usage behavior daily to provide a more creative experience.
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
CVPR paper: Instruct-Imagen: Image Generation with Multi-modal Instruction Innovations: - Multi-modal instruction for image generation: A new format that uses natural language to combine different modalities (text, edge, style, subject, etc.) to articulate complex generation intents in a uniform way. - Two-stage training approach for Instruct-Imagen: a) Retrieval-augmented training: Adapts a pre-trained text-to-image model to handle multi-modal inputs using retrieved similar (image, text) pairs. b) Multi-modal instruction-tuning: Fine-tunes the adapted model on diverse image generation tasks paired with multi-modal instructions. - Unified model architecture that can handle various image generation tasks - through multi-modal instructions, without task-specific designs. - Zero-shot generalization capability to unseen and more complex image generation tasks. - Adaptability to new tasks through fine-tuning on small datasets. source: https://arxiv.org/abs/2401.01952
0 reply
0 recast
1 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Curious the perplexity ai performance if put same query in it
0 reply
0 recast
0 reaction
ETH Investors Club pfp
ETH Investors Club
@eic.eth
Stoked to collab with /basepaint on this theme and look out for it in EIC02 Just minted 3 NFTs of Day 315 on BasePaint! Hundreds of pixel artists made this together on the blockchain. Minting is open only for 24h
0 reply
2 recasts
4 reactions
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Prepare for my summary of next CVPR2024 paper
0 reply
0 recast
1 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
CVPR 2024 Best Paper Award: Rich Human Feedback for Text-to-Image Generation - First dataset with detailed human feedback on generated images. - Rich Automatic Human Feedback (RAHF) Model (Multimodal Transformer model to predict rich human feedback) So, it enables that: - Finetuning generative models using predicted scores. - Region inpainting using predicted implausibility heatmaps. - Using aesthetic scores for classifier guidance in diffusion models. https://arxiv.org/abs/2312.10240
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
I will post the gem papers I found at the CVPR 2024 conference daily here. They are either (1) innovative in new model architectures, (2) new ways to facilitate model development, or (3) fun applications with full potential.
0 reply
0 recast
0 reaction
dylan pfp
dylan
@dylsteck.eth
brb need to go see how much I can build on top of this πŸ‘€πŸ‘€ https://github.com/jina-ai/reader
7 replies
1 recast
19 reactions
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Minted an NFT for contributing to @jessepollak's baldness. Onchain Summer Buildathon is based. Mint yours by joining the Onchain Summer Buildathon. https://letsgetjessebald.com/token/854?ref_code=63421e6a18
0 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
what the most innovative features on recaster?
1 reply
0 recast
0 reaction
POV:Frank (d/acc) 🎩 πŸ’œ pfp
POV:Frank (d/acc) 🎩 πŸ’œ
@scalinglaw.eth
Looking forward to this
0 reply
0 recast
0 reaction