Updated: Aug 19, 2024
styleNot loaded
Download
1 variant available
203
1.4K
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.
![Single_Image_Lora_Test_2_-_Flux_e000003_02_20240818222828[1].png](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/50425d6a-0e69-43e3-85b2-41f3bc6b0a68/anim=false,width=800,optimized=true/Single_Image_Lora_Test_2_-_Flux_e000003_02_20240818222828[1].jpeg)
Trained on one image, training tags were: colored skin, colored sclera, looking at another, 2girls, glowing eyes, profile, portrait, breasts
V1:
The sample images show the lora ran at various weights. I'm still testing combinations of weight/cfg/tags/etc to see what happens, and currently am training another with the same image but different training parameters.
V2e3:
Not necessarily better, just trained different.
I think V1 is the better of the two. With V1 I used autotagging set to .3, and just removed the tags that obviously had nothing to do with the image. It was also trained mostly on default settings. V2 I limited to just 2 tags and used different training parameters (adafactor instead of adam8bit, larger DIM)
I think I'm done experimenting with FLUX for the time being, training is expensive and generating images adds up quick.