Instructions to use d1ngdongji/MCSkin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use d1ngdongji/MCSkin with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-9B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("d1ngdongji/MCSkin") prompt = "Generate a 64x64 pixel texture maps of this Minecraft character" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| widget: | |
| - output: | |
| url: images/Flux2-Klein-9b-base_00001_.png | |
| text: Generate a 64x64 pixel texture maps of this Minecraft character | |
| base_model: black-forest-labs/FLUX.2-klein-9B | |
| instance_prompt: Generate a 64x64 pixel texture maps of this Minecraft character | |
| license: apache-2.0 | |
| # MCSkin | |
| <Gallery /> | |
| ## Trigger words | |
| You should use `Generate a 64x64 pixel texture maps of this Minecraft character` to trigger the image generation. | |
| ## Download model | |
| [Download](/d1ngdongji/MCSkin/tree/main) them in the Files & versions tab. | |
| ## Input image | |
| Using this prompt in nanobanana pro to generate input image: | |
| ``` | |
| # 生成[图1]中角色的Minecraft形象 | |
| - 人物模型必须与minecraft的玩家模型相同,且为包含内层/外层贴图的双图层模型,不能有额外元素。材质不能高于Minecraft所支持的分辨率。模型参考[图2] | |
| - 生成的minecraft角色的姿势与[图2]一致,且必须包含正面图与背面图,并排放置 | |
| - 在上述约束下,尽可能完美、准确的还原[图1]中的角色,包括外貌特征、全身所有服装、各种饰品等(不包括手持物品) | |
| ``` | |