Text-to-Image
Diffusers
stable-diffusion

Training code

#1
by gutianpei - opened

Very interesting work! I wonder if the authors plan to release the training code as well?

ByteDance org

We are currently not planning on releasing the training code.

Hi author, Could you mind releasing a version of LoRAs for A1111 stable-diffusion-webui?

Unfortunate that we aren't getting training code, but I get why there may be issues or extra challenges adapting it for public release. Thanks for the transparency.

ByteDance org

Hi author, Could you mind releasing a version of LoRAs for A1111 stable-diffusion-webui?

Hum, does A1111 have a different format? does our checkpoint not just work?

Hi author, Could you mind releasing a version of LoRAs for A1111 stable-diffusion-webui?

Hum, does A1111 have a different format? does our checkpoint not just work?

A1111 need a single safetensor file containing the whole model, including unet, vae, tokenizer, etc. Check sdxl's safetensor file example https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors

ByteDance org

@neogong Added!

gutianpei changed discussion status to closed

Sign up or log in to comment