Download
1 variant available
This is epoch 12, the rest are here: tensor.art/models/824670962764068377/Mixed-Media-Collage-1-NoCD6C5-2025-01-30-21:38:03-Ep-12
FLUX.1 - dev-fp8
Trigger: mixed media collage
Repeat: 20 Epoch: 12 (Trained on 19 512x512 images for 4560 total steps)
Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamW
Network Dim: 6 Alpha: 3
Epoch Loss
1 0.430
...
3 0.417
4 0.407
5 0.396
6 0.387
7 0.368
8 0.360
9 0.355
10 0.357
11 0.351 <- lowest
12 0.343
Show more

3.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
4.8K0 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.
This LoRA will generate colourful, mixed media collage style images of African Americans.
By default, people generated by this LoRA will be African Americans. You can try to generate other ethnicities, but it is pretty hard to do, except for people well known to the Flux base model, such as Alice in Wonderland. I suppose you can try to lower the weight of the LoRA if you really want to do that, but that kind of defeats the purpose of the LoRA.

