Downloads · 30 days
11
17% of all-time downloads
sammy-krea-v5-loras
jayark/sammy-krea-v5-loras
sammy-krea-v5-loras is a machine learning model from jayark. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as other.
Selected production candidates from the Sammy Krea v5 checkpoint evaluation:
All-time downloads
63
Public
Repo size
939 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors939 MB · 100%
At a glance
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Aug 12, 2026
- Updated
- Aug 12, 2026
- SHA
- 0f23e8a1
Base models
Model card
From the Hugging Face model README
Sammy Krea v5 LoRAs
Selected production candidates from the Sammy Krea v5 checkpoint evaluation:
- Character identity: step 800, trigger
sammy - General visual style: step 1400, trigger
sammy style
Fal-compatible files
Use the files in fal-compatible/ with fal-ai/krea-2/turbo/lora. They use
Diffusers-style Krea 2 LoRA keys and were verified through Fal's queue API.
fal-compatible/sammy-character-krea2-v5-step800.safetensors- SHA256:
2427e1344033434a0e18e81f11c01762c947b9464480c71db4b2583b18a810e6
- SHA256:
fal-compatible/sammy-style-krea2-v5-step1400.safetensors- SHA256:
551d60ec904e9c677750dcad97143cb563c712bf33fb2967f7d846126176dc2b
- SHA256:
The root-level checkpoints are the original musubi-tuner outputs. They work in the native musubi inference pipeline but must not be passed directly to Fal's managed Krea 2 endpoint. Fal can accept those URLs without applying the weights.
The adapter weights are subject to the Krea 2 base model's community license and any applicable rights in the training material.
- Library
- diffusers
- License
- other
- Created
- Aug 12, 2026
- Updated
- Aug 12, 2026