zer0int's picture

zer0int

zer0int

·

https://ko-fi.com/zer0int

AI & ML interests

I 💙 CLIP ~ 🤓🫶🤖

Organizations

New activity in zer0int/LongCLIP-KO-LITE-TypoAttack-Attn-ViT-L-14 2 months ago

Is it possible fine-tune this model?

#1 opened 2 months ago by

New activity in zer0int/clip-vit-large-patch14-336-text-encoder 5 months ago

Models?

#1 opened 5 months ago by

New activity in zer0int/LongCLIP-GmP-ViT-L-14 5 months ago

AssertionError: You do not have CLIP state dict!

#2 opened over 1 year ago by

PixelClassisist

New activity in BLISS-e-V/SCAM 6 months ago

Thank you for this dataset!

#7 opened 6 months ago by

New activity in zer0int/LongCLIP-Registers-Gated_MLP-ViT-L-14 6 months ago

i'm freaked out , what model should i ise , newest ?

#1 opened 7 months ago by

New activity in zer0int/CLIP-GmP-ViT-L-14 8 months ago

Max sequence length 88 > 77

#17 opened 8 months ago by

New activity in zer0int/CLIP-GmP-ViT-L-14 9 months ago

Does this fix the 20 token problem?

#16 opened 9 months ago by

New activity in zer0int/CLIP-Registers-Gated_MLP-ViT-L-14 10 months ago

Pure CLIP (no T5) guidance, but how ?

#1 opened 10 months ago by

New activity in zer0int/CLIP-GmP-ViT-L-14 10 months ago

Just reinstalled comfy and i don't remember what CLIP i need...

#15 opened 10 months ago by

New activity in zer0int/LongCLIP-GmP-ViT-L-14 10 months ago

Is the SeaArtLab node necessary?

#8 opened 11 months ago by

New activity in zer0int/CLIP-SAE-ViT-L-14 11 months ago

Are there any differences between the Full-model and TE-only versions?

#3 opened 12 months ago by

New activity in zer0int/CLIP-GmP-ViT-L-14 12 months ago

this only for sdxl and not ponyxl or Illustrious?

#14 opened 12 months ago by

New activity in zer0int/CLIP-SAE-ViT-L-14 12 months ago

Why don't any of these work with pony based XL?

#2 opened 12 months ago by

New activity in zer0int/CLIP-GmP-ViT-L-14 12 months ago

SwarmUI

#13 opened 12 months ago by

New activity in zer0int/LongCLIP-GmP-ViT-L-14 12 months ago

Your LongClip and sd1.15

#6 opened about 1 year ago by

Update config.json to include "max_position_embeddings"

#7 opened 12 months ago by

New activity in zer0int/CLIP-SAE-ViT-L-14 about 1 year ago

is this or the my-gmp one better for SD 3.5 large?

#1 opened about 1 year ago by

New activity in zer0int/CLIP-GmP-ViT-L-14 about 1 year ago

Recommended for Stable Diffusion 3.5 Large?

#12 opened about 1 year ago by

Are the long (248) vs short (77) text enhancing models similar quality for great text? and just different token length compatability?

#11 opened about 1 year ago by

Is it okay to use for Flux Lora training?

#8 opened about 1 year ago by