Sign In

Z_phyr FLUX Immersive Photorealistic (LoRA)

34
303
208
18
Verified:
SafeTensor
Type
LoRA
Stats
303
208
Reviews
Published
Nov 21, 2024
Base Model
Flux.1 D
Hash
AutoV2
1DFADD058C
default creator card background decoration
SDXL Training Contest Participant
Z_phyr's Avatar
Z_phyr
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.

LoRA is trained, first, to recreate the environment as if filmed on a phone, and second, it allows the first-person viewer to interact with that environment, mostly with their hands. Note that I consider the optimal model strength to be 0.5 (maximum 0.66) and clip strength to be 0.8. You can use it with other LoRAs, but be sure to lower their model strength to at least 0.66.

ЛоРА обучена, во-первых, воссоздавать окружающую действительность, будто снятую на телефон, а, во-вторых, позволяет зрителю от первого лица взаимодействовать с этим окружением, в основном руками. Обратите внимание, я считаю оптимальными силу модели 0.5 (максимум 0.66), а силу клипа 0.8. Можно использовать с другими ЛоРАми, но не забудьте понизить силу модели у них хотя бы до 0.66.