Verified: 4 months ago
SafeTensor
Type | |
Stats | 180 8 |
Reviews | (29) |
Published | Nov 22, 2024 |
Base Model | |
Training | Steps: 14,000 Epochs: 1 |
Usage Tips | Clip Skip: 1 Strength: 0.8 |
Hash | AutoV2 61CE9C1160 |
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.
This is a portrait style Lora based on F1d. It performs well in terms of facial features and hairstyles.
What interesting things can you do with it?
1. txt2img (output your imaginary characters and pets)
2. img2img (Generate anime style using your images, Denoising strength: 0.6-0.8)
The next optimization direction is scene and facial expressions.
After arcane2 is over, I will focus on outputting the style of an animated scene. I think it's necessary to train in two different cities separately