Instructions to use Xrenya/TheGhostInTheShellSD3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Xrenya/TheGhostInTheShellSD3.5 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Xrenya/TheGhostInTheShellSD3.5", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| library_name: diffusers | |
| tags: | |
| - Text-to-Image | |
| - Safetensors | |
| - StableDiffusionPipeline | |
| # Model Card for Model ID | |
| <td align="center"><img src="images/finetuned_seed_77_target_promt.png" width="512" height="512" alt="Motoko Kusanagi"></td> | |
| Seed: 77 | |
| <table> | |
| <tr> | |
| <th align="center"><b>Anime reference</b></th> | |
| <th align="center"><b>SD3.5 "anime kusanagi"</b></th> | |
| <th align="center"><b>SD3.5 "anime ohwx kusanagi"</b></th> | |
| <th align="center"><b>Finetuned SD3.5 "anime ohwx kusanagi"</b></th> | |
| </tr> | |
| <tr> | |
| <td align="center"><img src="images/kusanagi_reference.png" width="256" height="256" alt="original image"></td> | |
| <td align="center"><img src="images/baseline_seed_77_no_target_promt.png" width="256" height="256" alt="sd1.5 baseline"></td> | |
| <td align="center"><img src="images/baseline_seed_77_target_promt.png" width="256" height="256" alt="sd1.5"></td> | |
| <td align="center"><img src="images/finetuned_seed_77_target_promt.png" width="256" height="256" alt="sd3"></td> | |
| </tr> | |
| </table> | |
| Seed: 42 | |
| <table> | |
| <tr> | |
| <th align="center"><b>Anime reference</b></th> | |
| <th align="center"><b>SD3.5 "anime kusanagi"</b></th> | |
| <th align="center"><b>SD3.5 "anime ohwx kusanagi"</b></th> | |
| <th align="center"><b>Finetuned SD3.5 "anime ohwx kusanagi"</b></th> | |
| </tr> | |
| <tr> | |
| <td align="center"><img src="images/kusanagi_reference.png" width="256" height="256" alt="original image"></td> | |
| <td align="center"><img src="images/baseline_seed_42_no_target_promt.png" width="256" height="256" alt="sd1.5 baseline"></td> | |
| <td align="center"><img src="images/baseline_seed_42_target_promt.png" width="256" height="256" alt="sd1.5"></td> | |
| <td align="center"><img src="images/finetuned_seed_42_target_promt.png" width="256" height="256" alt="sd3"></td> | |
| </tr> | |
| </table> | |
| ## Model Details | |
| ### Model Description | |
| <!-- Provide a longer summary of what this model is. --> | |
| This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated. | |
| - **Developed by:** Xrenya | |
| - **Model type:** `stabilityai/stable-diffusion-3-medium` | |
| - **License:** `stabilityai/stable-diffusion-3-medium` | |
| - **Finetuned from model:** The Ghost in the Shell 2026 Anime | |
| - **Prompt:** "anime ohwx kusanagi" | |
| - **Baseline prompt:** "anime kusanagi" | |
| ### Model Sources | |
| - **Repository:** [Xrenya/stable_diffusion](https://github.com/Xrenya/stable_diffusion) | |
| The LoRA weights are provided in the repo, please download the official SD3.5 model and add lora config and weights in order to use the finetuned model on Motoko Kusanagi in anime "The Ghost In The Shell" 2026. |