Zero-Shot Image Classification
Transformers
Safetensors
clip
Inference Endpoints

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

#1
by mimizukari - opened

(assuming they're compatible since all notes always mention flux ;_;)

I don't know, I haven't tried SD-3.5 as I am not much generating images, but generating models (Text Encoders) these days. Also, it may depend on the image you're making. I suggest just trying it and maybe posting your results, so somebody else with the same question will certainly be grateful for that. =)

I think out of all it seems like the gmp text one works the best for sd3.5l, improving quality & fixing the text projection error.

Sign up or log in to comment