# Image2image SDLX finetuning using python **URL:** \ **Category:** 🧨 Diffusers\ **Created:** [February 24, 2025, 11:27am UTC](https://discuss.huggingface.co/t/image2image-sdlx-finetuning-using-python/142654 "2025-02-24T11:27:08Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![EgorKolpakov](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/egorkolpakov/32/41854_2.png) [@EgorKolpakov](https://discuss.huggingface.co/u/EgorKolpakov)\ **Post date:** [February 24, 2025, 11:27am UTC](https://discuss.huggingface.co/t/image2image-sdlx-finetuning-using-python/142654/1 "2025-02-24T11:27:08Z")
Hi guys, Don’t know which category I should pick but… Recently I faced with an issue. I want to create a script to fine-tune SDXL on my local machine using GPU. I want to train the model on the set of images with masking and without. Basically the task is that it has an image and in a certain region it generates polygons or something I want to place there. I have this paired dataset already. The result should looks as following. In the inference.py I give an image and the prompt, and model modifies the image. I started to surf the internet to have an example for this type of generation. But unfortunately all I see is a low-code or no-code solutions. Or solutions which got somewhat outdated due to multiple changes introduced by HuggingFace hub. I tried multiple ways how to make it but all the time I’m facing with some weird errors, which I’m not always able to address. If you have a code snippet that could help me out to fine tune model, save it and then inference, please let me know. 🙏🙏🙏 Thank you in advance! ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [February 24, 2025, 1:49pm UTC](https://discuss.huggingface.co/t/image2image-sdlx-finetuning-using-python/142654/2 "2025-02-24T13:49:43Z")
Is there anything similar to Inpainting or existing ControlNet? SDXL is not a model architecture specialized for image processing, so I don’t think there are many options. > **[Inpainting](https://huggingface.co/docs/diffusers/using-diffusers/inpaint)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. > **[ControlNet with Stable Diffusion XL](https://huggingface.co/docs/diffusers/v0.32.2/api/pipelines/controlnet_sdxl)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. > **[Spaces - Hugging Face](https://huggingface.co/spaces?category=image-editing)** > > Discover amazing ML apps made by the community ---
**Author:** ![EgorKolpakov](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/egorkolpakov/32/41854_2.png) [@EgorKolpakov](https://discuss.huggingface.co/u/EgorKolpakov)\ **Post date:** [February 25, 2025, 10:34am UTC](https://discuss.huggingface.co/t/image2image-sdlx-finetuning-using-python/142654/3 "2025-02-25T10:34:58Z")
Is it possible to finetune Kadinsky for certain image generation? ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [February 25, 2025, 12:25pm UTC](https://discuss.huggingface.co/t/image2image-sdlx-finetuning-using-python/142654/4 "2025-02-25T12:25:06Z")
It seems that fine-tuning is possible, but the sample is old, so it is unknown whether it will work as is. Basically, in this type of model, the training results for Text-to-Image also directly affect Image-to-Image. > **[GitHub - ai-forever/Kandinsky-2: Kandinsky 2 — multilingual text2image latent...](https://github.com/ai-forever/Kandinsky-2)** > > Kandinsky 2 — multilingual text2image latent diffusion model