CinEro-NoiceAI-XL

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 
 R8 A4 (CLIP Skip 2)
 
 = Based on R8 Alpha2. More training with same dataset. Very creative and surreal. Better surrealistic aesthetic than in R8 A2 and much more rich composition and details that in R8 A3 DMD.

<hr/>

 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R8 A4

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 
 R8 A2 (CLIP Skip 2)
 
 = Based on R8 Alpha1. More training with new dataset (realistic, creative, dark scifi and horror, nature, male and female characters, some animals and anthro). Anatomy (limbs, fingers, eyes) and textures are still cooking. Aesthetics, colors, clarity and realism shows noticeably better than R8 A1.

<hr/>

 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R8 A2

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 
 R7 Final XL (CLIP Skip 1)
 
 = I worked very hard to deliver the look of real life photographs made with regular-grade digital cameras with mid-grade attachable lens. Big attention was payed to the quality of anatomy (limbs anatomical correctness and natural pose), eyes (for ex., uneven eyes issue fix), fingers (finger number issue fix), background consistency (basically, fixing of the issue when straight lines in background don't match). I cannot say that this version fixes it all, but I tried to lower the chance of such issues to appear to the low level. I will continue to work on fighting the mentioned issues while trying to increase the creativity and the realism and details of the textures.

<hr/>

 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R7 Final XL

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 
 R7 smol soft [EXPERIMENTAL RELEASE VERSION]
 
 = It was trained in Full Fine Tuning mode with BF16 precision. CLIP Skip 2 used during training, but CLIP Skip 1 seems also working and gives more sharp renders. Trained version was quantized into FP8 for lower grade computers and lower VRAM requirements.


 Low-weight mixture of R7j RC2 applied for better stability and style inheritance.


 Goal of training: more detailed and complex backgrounds; improvements of eyes, fingers and structural consistency in background (straight lines matching); contrast and colors control in prompts. Quick tests show the improvements of eyes, fingers and textures. R7j had too sharp unnatural textures in some cases. This version has the chance of unnatural textures lower.

<hr/>

 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R7 smol soft

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 
 R7j RC2
 
 = Improved realism (lighting, colors, skin texture) and sharpness. Decreased chance of duplication at high resolution. For Single Pass Text-to-Image use DPM (better textures) or Euler A (smoother). Steps 8 gives smooth draft with simplified composition but more stable anatomy and env structures. Steps 40 w/ DPM gives good texture and mostly stable anatomy.

<hr/>

 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R7j RC2

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 
 R7i RC LowDMD
 
 == R7 Release Candidate. Most features delivered. Quick tests show good results. Kindly request for deeper tests. I need your support so hard to identify things that needs to be fixed / improved! Please comment and post your samples to highlight explicitly things that go not so well. Detailed and constructive critics are welcome as usual.

<hr/>

 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R7i RC LowDMD

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 
 R7f Beta LowDMD
 


 Improved performance even in 1pass workflow with Euler A + Karras, CFG 3.0+, steps 30+, high resolution like 1440x832 or 1280x1024... BLA-BLA-YADA-YADA FURTHER MARKETING BS...


 Consider it as Beta release because I'm not fully satisfied with eyes and fingers stability. Also, in some cases I'm not fully satisfied with textures and some samplers behavior.


 But in comparison with Alpha* releases of R7 it shows noticeably better performance in anatomy, lighting, textures, etc.

<hr/>

 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R7f Beta LowDMD

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 


 Yet another alpha build. Result of training on 3 new datasets. Still flawy (eyes and fingers on distant characters). But it should better support traditional SDXL settings (non-DMD, non-LCM renders).


 Rule for steps: 8 steps kinda works but gives smooth picture like LCM sampler but with any samplers; 16 steps starts to give details using contrast samplers like DPM++ 2S A; 25..30 steps sharp enough for single pass render, but small objects like eyes and fingers might be unstable; not yet tested on 40+ steps, but I don't expect significant quality improvement.


 Euler A with CFG up to 6.0 and steps from 14 and greater works as LCM sampler for previous (DMD2 versions). Euler A gives low noise, very smooth pictures. Good for Text2Image with consequent HiRes fix using other samplers.


 DPM++ 2S A + Karras with CFG near 2.5 and steps 20+ is good for realism and texture rendering/optimal to me as a Text-to-Image.

R7d Alpha2 NoDMD

Creator:
 <a href="https://civitai.com/user/homoludens" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/homoludens
 </a>




 
 
 About this version
 
 

<ul>
 <li>
 
 
 SMOOTH:
 
 Euler A; steps 8; CFG 1.5 or more;
 
 </li>
 <li>
 
 
 SHARP:
 
 Euler / Euler A / steps 14 or more gives a very sharp result (good to render wet surfaces or glass); steps 8..12 looks optimal to me as a Text-to-Image.
 
 </li>
</ul>