Verified: 6 months ago
SafeTensor
Type | |
Stats | 278 |
Reviews | (32) |
Published | Aug 16, 2024 |
Base Model | |
Training | Steps: 4,000 |
Hash | AutoV2 49385144F0 |
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.
Weight:0.65~0.8
Recommended to use together:Crayon Style
Using this Lora, you can get the most beautiful street views in Taiwan. Since I used a lot of Google Maps material, people's faces are blurred, and there are strange road names on the ground. I don't know why this Lora training results in blurriness, but applying a 'Pencil Drawing' Lora solves this problem well.
このロラを使えば、台湾で一番美しい街並みを見ることができます。Googleマップの素材をたくさん使っているので、人々の顔はぼかされていて、地面には奇妙な道路の名前が書かれています。なぜこのLoraのトレーニング結果がぼやけてしまうのかはわかりませんが、「鉛筆画」のLoraを適用するとこの問題はうまく解決します。
一堆違停闖紅燈有掌握到精隨
一開始產圖都超糊,後來套了鉛筆畫這個lora就穩了一點
具體原因不知道..