Downloads · 30 days
0
z-image-lokr-repro
scenario-labs/z-image-lokr-repro
z-image-lokr-repro is a machine learning model from scenario-labs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Random weights — not a functional adapter. This file reproduces the key layout of a real Z-Image LoKr trained with an ai-toolkit/LyCORIS-style trainer (ComfyUI diffusionmodel. key format), for reproducing https://gith…
Access
Public
Updated Jul 9, 2026
Repo size
585 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors585 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026
- SHA
- 8d751108
Base models
Model card
From the Hugging Face model README
Z-Image LoKr — diffusers loading repro
Random weights — not a functional adapter. This file reproduces the key layout of a real
Z-Image LoKr trained with an ai-toolkit/LyCORIS-style trainer (ComfyUI diffusion_model. key
format), for reproducing https://github.com/huggingface/diffusers/issues/13221.
ZImagePipeline.load_lora_weights / lora_state_dict fails on it with
ValueError: state_dict should be empty at this point because
_convert_non_diffusers_z_image_lora_to_diffusers has no handling for lokr_w1 / lokr_w2 keys.
from diffusers import ZImagePipeline
from huggingface_hub import hf_hub_download
path = hf_hub_download("scenario-labs/z-image-lokr-repro", "zimage_lokr_dummy.safetensors")
ZImagePipeline.lora_state_dict(path) # raises ValueError on diffusers <= 0.39 / main
Layout (612 tensors, 30 layers)
Mixed LoKr + plain LoRA:
| module | format | layers | shapes |
|---|---|---|---|
attention.to_q/k/v | LoKr | all 30 | lokr_w1 [4,4], lokr_w2 [960,960], scalar alpha |
adaLN_modulation.0 | LoKr | all 30 | lokr_w1 [4,4], lokr_w2 [3840,64], scalar alpha |
attention.to_out.0 | LoRA | 0–17 | lora_A [32,3840], lora_B [3840,32] |
attention.to_out.0 | LoKr | 18–29 | lokr_w1 [4,4], lokr_w2 [960,960], scalar alpha |
feed_forward.w1/w2/w3 | LoRA | all 30 | rank 32 |
The same file loads fine in current ComfyUI (which fuses to_q/k/v into attention.qkv and
supports LoKr via comfy/weight_adapter/lokr.py).
- License
- apache-2.0
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026