Text-to-Image
Diffusers
Safetensors
English
ZImageAnyFlow2Pipeline
z-image
anyflow2
distillation
custom-pipeline
Instructions to use kimi000/ZImage-4Step-3000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kimi000/ZImage-4Step-3000 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-4Step-3000", 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 validation.json from kimi000/ZImage-4Step-3000: direct link, hf CLI and curl.
- Browser
- Download file 385 Bytes
-
https://huggingface.co/kimi000/ZImage-4Step-3000/resolve/main/validation.json
- Command line
-
hf download hf://kimi000/ZImage-4Step-3000/validation.json
-
curl -L -o validation.json https://huggingface.co/kimi000/ZImage-4Step-3000/resolve/main/validation.json
385 Bytes
| { | |
| "real_ema_merge": "bitwise_exact_peft_bf16_projection", | |
| "pipeline_load": "passed", | |
| "smoke_resolution": 1024, | |
| "training_and_demo_resolution": 1024, | |
| "pixel_std": 85.7381439388038, | |
| "global_step": 3000, | |
| "weights": "ema", | |
| "device": "cuda", | |
| "transformer_calls": 4, | |
| "inference_seconds": 2.988361120223999, | |
| "cpu_offload": "passed", | |
| "four_step_end_to_end": "passed" | |
| } | |