- Flux ControlNets with Txt2Img | Img2Img | + Multiple LoRAs, All in one notebook
- Works in Google Colab Free Teir T4 GPU 🥳🥳
- Uses Flux.1-dev GGUF models
Notebook | Info |
---|---|
Flux.1-dev-XLabs_CN-jupyter (flux1-dev-Q4_K_S.gguf) | |
Flux.1-dev-Union_CN-jupyter (flux1-dev-Q2_K.gguf/Q8_0.gguf) |
* This is still unstable in google colab free tier and prone to crashing because of low system RAM. Use at your own risk.
Basic Functions [Txt2Img | Img2Img | + Multiple LoRAs] are as shown in LucipherDev/Flux.1-fp8-jupyter
- Canny
- Depth (DepthAnythingV2)
- HED
Low RAM uses flux1-dev-Q2_K.gguf and gives low quality results, so using high RAM is advised as it uses flux1-dev-Q8_0.gguf
- Openpose
- Depth (DepthAnythingV2)
- HED
- Pidi
- Scribble
- Ted
- Canny
- Lineart
- Anime_lineart
- MLSD
- Normal
- Segment