Cinematix Inpainting (NEW)

In Forge, set XL as your model type and select cinematix.inpainting.safetensors as your model. Go to Img2img tab to Generation/Inpaint. Load your image and mask the area you want to change. Set a simple prompt describing the changes. Generate. Change the Denoising strength if you want a stronger effect. You should get nice outputs right away.

Experiment with Inpaint area Whole picture/Only masked. If using Whole picture, set the image size to your input image aspect ratio.

Also worth checking out:

Cinematix CosXL EDIT is realistic SDXL Pix2Pix model for editing. It uses a different workflow and you can find it here:

https://civarchive.com/models/396070/cinematix-cosxl-edit

Cinematix L8 Inpainting

1. Use CFG 1.5-4 for 10-20 steps, Euler A, DPM++2Sa + SGMUniform schedule

2. Created for Flux experiments, check also Photomatix SD Inpainting model for fast sketches

Cinematix L8

Performs better in upscaling, needs more steps. Cinematic photo style.

1. Lightning Model, Use CFG 1.5 for 10-12 steps

2. For more steps, adjust CFG proportionally (~ CFG 2 for 24st., CFG 2.5 for 36st)

3. Works best with Euler A + SGMUniform schedule

Cinematix L4

Scenes should be better defined when using cinematic styles.

1. Lightning Model, Use CFG 1.5-2

2. Steps 7-12 for Euler A, DPM++ 2S a, and similar samplers for a nice single-pass image (should generate a nice picture with minimum artifacts)

3. More steps can be used for the LCM sampler

4. Recommended 'Euler A SGMUniform' sampler (Forge)

5. For best details, experiment with a 2-pass workflow (in A1111, use Hires fix tweaks and LCM in the second pass)

Cinematix Lightning

1. Use CFG 1.5

2. steps 5-12 in a single pass for a nice picture

3. LCM or Euler A SGMUniform sampler (standard samplers can/will output strange colors or artifacts)

4. 2-pass can use 3-4 steps + 3+ steps in Hire fix, Denoising strength around 0.5

5. Note that SDXL-Lightning performs best in resolutions around 1024

More about the workflows in this article on [sandner.art].

Cinematix SDXL v1

Cinematix is a very fast realistic SDXL model. Read more details in an extensive article on my pages.

1. You may use standard samplers with lower steps 5+ (but you should go higher), recommended 12 steps for most scenes

2. Samplers: DPM++ 2S a, LMS Karras, Euler a (LCM not performing well in low steps)

3. You may use Photomatix and Animatix experimental styles for great results. Download them here. Read the instructions first. There are classic SDXL styles for your reference tests too.

4. You may use higher CFG (4-7+), instead of the usual LCM CFG 1.5.

5. An extensive negative prompt is NOT needed. Actually, in most cases, the negative prompt is not needed at all. Check the gallery for examples.

6. You may be very brief when prompting. Examples in the gallery are for comparison with my previous checkpoints and posts.

If you create something interesting with it, post a review.

Cinematix was created by merging and experimenting with these models:

StabilityAI SDXL

OpenDalle

Hephaistos

RaffaelloXL

SDXL-Lightning https://huggingface.co/ByteDance/SDXL-Lightning, https://arxiv.org/abs/2402.13929

L8:

HalcyonSDXL

NewReality