Text-to-Image
Diffusers
Safetensors
GGUF
English
image-generation
diffusion
anime
z-image
z-anime
comfyui
fp8
bf16
aio
Instructions to use SeeSee21/Z-Anime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SeeSee21/Z-Anime with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SeeSee21/Z-Anime", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Trying to train with AI-Toolkit but all samples look messed up
#14
by AIxFuneStudio - opened
I'm trying to train AI-Toolkit with: https://huggingface.co/SeeSee21/Z-Anime/tree/main/diffusers
But all samples look broken.
When I trained with Z-Image Turbo and Z-Image Base - they both work fine with AI-Toolkit.
Is there something special Z-Anime requires for samples?
A bug report I created for AI-Toolkit about messed up samples: https://github.com/ostris/ai-toolkit/issues/879
I received a solution with comment: https://github.com/ostris/ai-toolkit/issues/879#issuecomment-4697687013
Maybe it's worth investigating if text_encoder folder needs to be adjusted, to resolve this issue in this repository.