George0726

Hi folks, are there any other updates on the PR?

@Lakshmanaraja > Hi there, I want to fine-tune my ControlNet on my fine-tuned SD 1.5 inpainting models. However, I found that after 100 steps. My inpainting area became all black....

Hi jianbin, I found that TCM Lora cannot work well on Fine-tuned models, which is similar to LCM lora. Hence, I am trying to fine-tune a TCM LoRA on my...

Appreciating for your kindness! I will share some information with you privately

> > we add some early results in https://github.com/TencentQQGYLab/ELLA?tab=readme-ov-file#-emma---efficient-multi-modal-adapter-work-in-progress > > I reproduced a version of Ella based on SD XL, and the effect is really improved over the original...

> i am not sure they actually even did what they claim.. we have been trying to train it for ~2 months. it just doesnt work for sdxl since it...

> i dont think george is being honest about it. his issues opened on my project do not indicate a deep understanding of this type of work or the code...

> i dont think george is being honest about it. his issues opened on my project do not indicate a deep understanding of this type of work or the code...

Thanks for your PR for SD3 inpainting! I am currently trying to finetune the inpainting version by 33 channels. Your version raised an Error on inpainting-specific checkpoints. 1. the masked...

@IrohXu Sure. I have tested and modified some parts to make it work. 1. SD3 VAE added additional **self.vae.config.shift_factor** to normalize, you can refer to https://github.com/huggingface/diffusers/blob/49979753e14e7fed61bebd5700d4dbd1b14a6ffc/src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3_img2img.py#L629 2. masked_latent should also...