Sign In

Ultima Cine (Flux)

76

587

1.8k

16

Verified:

SafeTensor

Type

LoRA

Stats

191

1.2k

4.2k

Reviews

Published

Feb 26, 2025

Base Model

Flux.1 D

Training

Steps: 2,100
Epochs: 10

Usage Tips

Clip Skip: 1
Strength: 0.8

Hash

AutoV2
16C4718933
default creator card background decoration
AventraAi's Avatar

AventraAi

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.

Important Note:
1. Please keep in mind that this is an experimental LoRA. While it aims to provide improved results, performance may vary based on the input prompts and settings. Your feedback is valuable for further refinements.

Ultima Cine is a experimental Cinematic LORA, created to enhances the Flux model to create stunning, film-inspired visuals. It adds realistic lighting, dynamic color grading, and cinematic atmosphere to your images, perfect for scenes that require mood and depth. Ideal for generating high-quality artwork with a cinematic touch, whether for concept art, storyboarding, or visual storytelling.

v0.3:
Version 0.3 had been trained on refined dataset.

v0.2:
Version 0.2 has been trained on the complete dataset of training images from v0.1, as well as an additional set of widescreen images. As a result, v0.2 is optimized to deliver an improved cinematic look, with enhanced depth and visual quality.

v0.1:
Showcase images used following parameters in forge:
Steps: 20, Sampler: DEIS, Euler, Schedule type: Beta, CFG scale: 1, Distilled CFG Scale: 2.5

Keywords: Ultima cine, cinematic, high quality, realistic, film still, faded vintage photo, film grain, professional photo, golden hour, faded colors, soft focus, bokeh, background blur, lens flare, Fujifilm.