Sign In

Shinkawa [ Flux LoRA ]

11
122
140
7
Verified:
SafeTensor
Type
LoRA
Stats
122
140
Reviews
Published
Aug 18, 2024
Base Model
Flux.1 D
Training
Steps: 2,275
Epochs: 35
Usage Tips
Clip Skip: 1
Hash
AutoV2
CEFC7AA613
default creator card background decoration
Shadowheg's Avatar
Shadowheg
Created on Civitai
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Lora is trained on 512p artwork images by Yoji Shinkawa. The result is Lora for retro anime art.

Recommended to use Strenght model 0.7-0.8

This is my workflow with FLUX gguf DEV Q8 or Q4. Working with Lora, The Q4 is as fast as the NF4.