This is the UPDATE version of the Rockwelly S1 model.

Feel free to test and use it.

The Update Version follows the same principles as Version 1 (previous)!

Reason for updating Project S1:

1: Many errors were found in areas such as eyes and hands.

2: Due to the model's sensitivity to prompts (if the prompt wasn't detailed enough), the images don't come out uniform.

3: Compatibility with multiple loras.

Version S1 v1 at1 is an update version of the project. The issues mentioned above have been fixed.

Recommendations:

1: Know how to describe your prompt (putting things like "looking down" and then putting "looking up" in the same prompt) will cause aberrations in your generation. Therefore, REVIEW YOUR PROMPTS.

2: Note that (in this model's case), you can "play" with the Denoise. You can keep it at (low ha: 0.75) up to its maximum (high: 1.0). Doing so (with the seed fixed) will give you different effects and sometimes different results.

**SETTINGS**:

The Ksampler settings haven't changed much. However, you can have more freedom with the settings and steps.

Minimum recommendations:

Steps: 22

CFG: 1.4

Sampler_Name: Euler_A

Scheduler: Karras

For different effects, you can use Sampler_name: Res_Multistep with Scheduler: Sgm_uniform; they also give good results (depending on what you plan to do).

Once again, I humbly ask that if you liked this model, please post your creations and feedback after downloading it. This will help me understand how this model can be improved.

I use two versions of the template: one for creating the image and the other as a refiner. In the refiner, you reduce the noise reduction. Otherwise, unwanted objects or objects will appear. Since I use both templates, I know how high I can set the refiner's noise reduction. But I recommend leaving it at 25, 30, or 40, depending on what you intend to do.

Configuration:

Step 1 = Image Generation

(Ksampler: RES_MULTISTEP + SGM_UNIFORM / steps: 22 cfg: 1.5 / 1.4 (sometimes at 1) DENOISE AT 0.8 OR 1)

Step 2: Ksampler: LCM + BETA / steps: 22 or 30 CFG: 1.4 / 1.5

Step 3: Ksampler: Euler A + Karras / steps: 35 Cfg: 4.5 <<< This configuration creates more anime-style images. <<<<

Step 2 = Bug fixes in the Face, Hands, and Eyes Detailer (I rarely use it because the model defines the hands and face well, especially if you use a refiner.)

Step 3 = UpScale and DownScale

(I leave the Upscale at 2x AnimeSharpv4_RCAN) (For anime images, and for realistic or semi-realistic images, I switch to RealESRGAN.)

Step 4 = Refinement

(Ksampler: euler_a +Karras / steps: 10 cfg: 1.0 / noise reduction: 0.30 or 20)

(Any value above 40 will modify your image and cause unwanted effects.)

Step 5 = Contrast adjustments and image post-processing.

Important detail.

As you can see in my frequently posted images, the image quality is better.

The reason is simple.

I work on the images separately.

Step 1 = Image generation

Step 2 = Error correction in Face Detailer, Hand, and Eyes

Step 3 = UpScale and DownScale

Step 4 = Refinement

Step 5 = Contrast adjustments and image post-processing.

So, don't just copy the prompt and wait for the magic to happen.

You'll need to put in some effort, whether with this model or any other.

REMEMBER:

"**AI-GENERATED IMAGES ARE LIKE PHOTOGRAPHS**.

THE MORE YOU DEDICATE TO MAKING AN IMAGE, THE CLOSER YOU WILL BE TO AN AMAZING IMAGE!

++++++++++^^^~^~^++++++++++++++^^~~^^~^~^^~~~~^~^^^^~~~~+++++++++++++++

And if you liked my work, follow me on social media. All the images I post on social media are generated from my models, whether test or finished versions.

Below is a summary of the first version with information about it.

Since this is my first model, there may be some flaws (nothing that is a problem and cannot be fixed with a refiner or a second attempt with KSampler or USDU (Ultimate Upscale)). Currently, my only priority has been trying to infuse the TensorArt TurboX LoRA 8-step [SD3.5 large] (https://civitai.com/models/1362210/tensorart-turbox-lora-8-steps-sd35-large) with one of my Checkpoint models and Qwen Image Lightning 4-8 steps

(https://civitai.com/models/1862507/qwen-image-lightning-workflow-4-8-steps).

The reason is clear:

"My graphics card is a GTX 1060/6GB," so you can see how much I struggle to generate good images.

That's why I've been working (slowly and carefully) on a checkpoint that allows me to balance speed and quality. ** IT'S NOT PERFECT YET (THE WAY I WANT IT), BUT IT'S ALREADY SURPRISED ME ENOUGH TO SHARE IT WITH YOU.

Please help with the testing and post your results. The current settings are:

Steps: 22

cfg: 1.0 / 1.5 (my recommendation is not to exceed this value if using EULER A)

Scheduler: Karras

I sometimes tested with Res_Multistep + Sgm_ufiform

Steps: 22 / 25

cfg: 1.0 / 1.5

The results were sometimes satisfactory.

This is because I tested with the simplest workflow possible.

Time to beg:

"If you liked this checkpoint and would like to support my work, please consider following me on social media and following me, as I will always be looking for ways to improve this project and develop new ones (even with the limited resources of a GTX 1060/6GB)."