Recommended Negative Prompts

(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D, 3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)

Recommended Parameters

samplers

DPM++ 2S a

steps

35

cfg

7

resolution

1564x768

Recommended Hires (High-Resolution) Parameters

upscaler

Juggernaut Aftermath, SDXL Refiner

upscale

1.5

Tips

You can refine RAW output with any model like SDXL Refiner or Juggernaut.

The cinematic LoRA is in early development with 35 epochs and around 3000 training steps.

Upscale outputs 1.5 times with Juggernaut Aftermath for enhanced details.

Version Highlights

Epoch 100

8100 Steps

Creator Sponsors

Try also my Other Stuff:

Juggernaut

Juggernaut Negative

If you want to make a donation/tip, feel free to check my Ko-Fi Page :)

Update:

Version 2 is ready with 8100 Steps, its now way more stable then the first release.
This Time the images are made with RunDiffusion XL .

Its just the RAW Output with the LoRA . You can refine it with every Model u like (for example : SDXL Refiner, RunDiffusion XL, Juggernaut ;) )

Hope to see some of your masterpieces in the gallery :)

Hi my Friends here I am again.

While Juggernaut is still in the queue, of course, I have tried first attempts with a few LoRAs. Most of the attempts were completely uninteresting and did not create any added value for the community, so I did not even upload them.

The SDXL base version already has a large knowledge of cinematic stuff.

However, I wanted to focus on it a bit more and therefore decided for a cinematic LoRA project. The whole thing is still in a really early stage (35 epochs, about 3000 steps), but already delivers good output :) (Better Cinematic Lighting for example, Skin Texture is a bit better)

The first 10 pictures are the raw output from SDXL and the LoRA at :1 The last 10 pictures are 1.5 upscaled with Juggernaut Aftermath (but you can of course also use the XL Refiner)

If you like the model and want to see its further development, feel free to write it in the comments. Post some of your creations and leave a rating in the best case ;)

Try also my Other Stuff:

Juggernaut

Juggernaut Negative

If you want to make a donation/tip, feel free to check my Ko-Fi Page :)

Contributor

Previous
Disposable Camera (for Flux) - v1.0
Next
Metal Gear Solid by ChronoKnight - [FLUX] - v1.0

Model Details

Model type

LORA

Base model

SDXL 1.0

Model version

Version 2

Model hash

4c113fd99f

Trained words

Movie Still
Film Still
Cinematic
Cinematic Shot
Cinematic Lighting

Creator

Discussion

Please log in to leave a comment.