Downloads · 30 days
1
11% of all-time downloads
quiet-canvas-27
kimi000/quiet-canvas-27
quiet-canvas-27 is a text-to-image model from kimi000. Use it when you need an image from a text prompt. It is set up for diffusers.
This is a complete native Diffusers Z-Image pipeline exported from zimagebasediffusionnftalphagrpodvrewardalphagrpo20k512px16stepcfg428prompts7train1dvrewardtp12nodenrt at Step 500. The EMA LoRA (rank 256, alpha 256)…
All-time downloads
9
Public
Parameters
6.2B
20.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors20.5 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- 94a0ba78
Model card
From the Hugging Face model README
Z-Image AlphaGRPO DVReward - Step 500 EMA
This is a complete native Diffusers Z-Image pipeline exported from
zimage_base_diffusionnft_alphagrpo_dvreward_alphagrpo20k_512px_16step_cfg4_28prompts_7train_1dvreward_tp1_2node_nrt
at Step 500. The EMA LoRA (rank 256, alpha 256) is merged into BF16 base
weights, so FAR and PEFT are not required for inference.
python demo.py --prompt "A red cube beside a blue glass sphere."
The helper uses CFG 4, fixed scheduler shift 6, dynamic shifting disabled, and an explicit 50-update sigma schedule ending at sigma 0.
- Task
- Text-to-Image
- Library
- diffusers
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026