Balanced CLIP (Updated)
Checkpoint
Pony
Checkpoint
Pony
PONY_CLIP_L

Balanced CLIP (Updated)

Felldude
Creator
⭐ 0.0
⬇ 1,278 Downloads
👁 1 Views
🖼 7 Images

About this model

Balanced CLIP (1M)

Training CLIP-G took >15KwH of energy, CLIP-L took far less <1KwH

The full negative reinforcement (Cosine Dissimilarity) is available on my huggingface, this was paired with a positive reinforcement (Contrastive Loss) using the full frozen vision model in latent space.

PONY CLIP-L has a further 10 epochs using ASGD for very fine-tuned loss.

Related Models

Similar AI models you may like