DarkViewAI

it also doesn't patch the lora, it just ignores it

> Temporal solution for testing: > > * Backup and change `config.json` at `webui\backend\huggingface\black-forest-labs\FLUX.1-dev\text_encoder_2\` > * Backup and change `tokenizer.json` at `webui\backend\huggingface\black-forest-labs\FLUX.1-dev\tokenizer_2\` > > Same for FLUX.1-schnell. > > Change...

i got it to work now, for some reason the files got over written again.

@b-fission yes, everything works fine with bf16 but its not with full-fp16

+1 Same for me as well

when it loads. Loading Model: {'checkpoint_info': {'filename': '/home/Ubuntu/apps/stable-diffusion-webui-forge/models/Stable-diffusion/flux1-dev.safetensors', 'hash': 'b04b3ba1'}, 'additional_modules': ['/home/Ubuntu/apps/stable-diffusion-webui-forge/models/VAE/ae.safetensors', '/home/Ubuntu/apps/stable-diffusion-webui-forge/models/VAE/clip_l.safetensors', '/home/Ubuntu/apps/stable-diffusion-webui-forge/models/VAE/t5xxl_fp16.safetensors'], 'unet_storage_dtype': None} [Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ......

when the lora model actually works, it doesn't look like the character i finetuned. the full checkpoint works as normal. but the extracted lora likeness is gone. prevously with sdxl...

Yeah still doesn't work, images are not like the samples in training, or the checkpoint. checkpoint works fine. the extracted lora images have no likeness to the character and most...

Hi i was using rank 128, so do i just add --multiplier=1.5

ohhh you mean when using the lora i do :1.5 is there a way to implement it into the extract ?