Download
1 variant available
4110 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
840 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2930 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(88)
Feb 14, 2025
This is epoch 10, the rest can be found at tensor.art/models/829955331611189609/Egyptian-Art-V1-CapD6A6Cos5-2025-02-14-03:41:07-Ep-10
FLUX.1 - dev-fp8
Trigger: egyptian
Repeat: 20 Epoch: 10 (Trained on 23 512x512 images for 4600 steps)
Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamW
Network Dim: 6 Alpha: 3
Epoch Loss
1 0.430
2 0.420
3 0.418
4 0.399
5 0.392
6 0.382
7 0.368
8 0.362
9 0.357
10 0.353 <- lowest
Show more

108.8K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
3.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
46.8K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

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.
Trained on twenty-three photos of Egyptian tomb paintings and bas-relief, most of them from the Tomb of Nefertari. To see more of these images, please go to:
https://www.flickr.com/photos/manna4u/albums/72157680132968381/
https://www.flickr.com/photos/manna4u/albums/72157699920931014/
The LoRA seems to work better with simpler prompts. When the prompt is too detailed, Flux will switch to its default photo style.
Please have fun and share your work for us to enjoy 🎈🙏😹

