Text-to-Image
Diffusers
Safetensors
English
ZImageAnyFlow2Pipeline
z-image
anyflow2
distillation
custom-pipeline
Instructions to use kimi000/ZImage-AnyFlow2-4Step-1000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kimi000/ZImage-AnyFlow2-4Step-1000 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kimi000/ZImage-AnyFlow2-4Step-1000", 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
Download export_metadata.json from kimi000/ZImage-AnyFlow2-4Step-1000: direct link, hf CLI and curl.
- Browser
- Download file 646 Bytes
-
https://huggingface.co/kimi000/ZImage-AnyFlow2-4Step-1000/resolve/main/export_metadata.json
- Command line
-
hf download hf://kimi000/ZImage-AnyFlow2-4Step-1000/export_metadata.json
-
curl -L -o export_metadata.json https://huggingface.co/kimi000/ZImage-AnyFlow2-4Step-1000/resolve/main/export_metadata.json
646 Bytes
| { | |
| "global_step": 1000, | |
| "weights": "ema", | |
| "format": "diffusers", | |
| "serialization": "safetensors", | |
| "lora_merged": true, | |
| "source_checkpoint": "step_1000_lora.pt", | |
| "source_sha256": "87e13b102ee3f3e79bdbab00d5027a84a3c576ebd94d2ac9ff3dfe90807ef9c6", | |
| "base_model": "Tongyi-MAI/Z-Image", | |
| "global_batch_size": 128, | |
| "training_resolution": 1024, | |
| "num_horizon_basis": 128, | |
| "coordinate_mode": "global", | |
| "shift": 6.0, | |
| "final_step_size_scale": 0.5, | |
| "distillation_teacher_cfg": 4.0, | |
| "inference_cfg": "none", | |
| "inference_steps": 4, | |
| "prompt_mix": { | |
| "MJHQ": 0.5, | |
| "TextAtlas": 0.25, | |
| "reward_prompt_dataset": 0.25 | |
| } | |
| } | |