Denis Malimonov

Added support for a new hint for colorization. [The model](https://huggingface.co/neurallove/controlnet-sd21-colorization/resolve/main/colorization-sd21-safe.safetensors) is trained on the base model Stable-Diffusion 2.1 (512) and is located on HF. Here's a [Colab](https://colab.research.google.com/drive/1pZW57lNvvdc-YcSKWt3N6dKj3OTFjmgg) for tests

Added support for a new hint for colorization. [The model](https://huggingface.co/neurallove/controlnet-sd21-colorization/resolve/main/control_v11u_sd21_colorization.ckpt) is trained on the base model Stable-Diffusion 2.1 (512) and is located on HF.

[WIP] Colorization + ControlNet

3

Hello, we have been trying (at [neural.love](https://neural.love/)) to train the colorization model based on the ControlNet architecture. The model was trained on different LR's on the manually collected b&w-colorful image...

If you use the 'RSBlur' model in deblur, an error is thrown. It is necessary to change the `gap` variable to `ap` in: /content/SFNet/Motion_deblurring/models/layers.py

After merging LORA and base model, random tokens are generated

2

I am facing a problem with merging lora and base model (Gemma2-9B). For pretrain, I haven't updated the tokenizer dictionary. I used the default one. After training I have a...