Verified: 3 months ago
SafeTensor
Type | |
Stats | 137 2 |
Reviews | (23) |
Published | Aug 17, 2024 |
Base Model | |
Training | Steps: 175 Epochs: 5 |
Usage Tips | Clip Skip: 1 |
Hash | AutoV2 841C3410BC |
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.
I saw a severe lack of style LORAs for Flux so decided to train on on the paintings of Vincent Van Gogh. The current model is somewhat under trained so I suggest Using a LORA weight of at least 3 to allow the style to be consistent but you can go anywhere from 2-4 depending on if you add prompts related to the art style in your prompts. Flux Guidance from 3.5 to 7 were tested.
Made with the Trainer on Civitai!