Text-to-Image
Diffusers
Safetensors
English
Korean
ZImagePipeline
image-generation
quantized
bitsandbytes
nf4
4-bit precision
on-device
korean
pocket
vidraft
8-bit precision
Instructions to use FINAL-Bench/POCKET-Image-Zimage with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FINAL-Bench/POCKET-Image-Zimage with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FINAL-Bench/POCKET-Image-Zimage", 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
Commit History
-
POCKET family: add POCKET-Qwen3.8-Flash-Next (180B on a laptop), cross-link all 8 POCKET repos
Verified signatured40c018 -
Add POCKET-Zimage-CPU badge (front)
Verified signature3d8cccf
-
Honest card: 4-bit NF4 Z-Image build + usage + Studio link
Verified signature5364f3d -
Add NF4 4-bit quantized Z-Image checkpoint (~6GB, on-device)
Verified signature910743a
-
POCKET family cross-links + Image/Studio/Zimage
Verified signature5a24750 -
initial commit
Verified signatureb8dae54