Verified: 5 months ago
SafeTensor
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 is trained on images from Hollywood films using the classic Technicolor 3-Strip process (think Wizard of Oz, Singin' in the Rain, and many of the vintage Bond films). As a result it doesn't just reproduce the tonality, but the overall visual style of those movies, including clothing and hairstyles.
Usage: keyword is 'tchnclr', but it only has a minimal effect so feel free to omit it.
Works well at a weight of 1. All the example images are stock Flux Dev with the Lora at weight 1 and no other processing.
At lower weights you can use it to get rid of the standard Flux 'look' for men and women. Above 1.5 it's going to do strange things.
It will tend to soften images, because movies of this era were generally pretty soft by modern standards. You can add 'sharp, high detail' etc if that offends you!
You can add terms like 'vintage', 'analog', 'cinematic', 'movie still' and 'technicolor' to see how it interacts (although I don't like what 'technicolor' does, hence this Lora).
Below, images with weight 0 and weight 1
