<h3 id="krea-2">Krea 2</h3>Showcase images :<ul><li>Turbo model : 8 steps / CFG 1 &amp; Euler simple</li><li>768x1152</li><li>x2 Hires (10 steps, 0.35 with 4x_NMKD_Siax)</li><li>Lora strength 1.2</li></ul>Can also do characters : Guts, Casca, Griffith.<h3 id="ideogram-4">Ideogram 4</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/54927a56-ba2b-4cb5-802a-f545da5b525f/original=true/54927a56-ba2b-4cb5-802a-f545da5b525f.jpeg" />Can do Guts, Casca and Griffith characters + the style.<h3 id="klein-9b">Klein 9B</h3>Showcase images :<ul><li>Distilled model</li><li>768x1152</li><li>Euler / normal / 4 steps / CFG 1</li><li>Lora strength of 1</li></ul><h3 id="zib">ZIB</h3>v1 :Still experimenting with Z-image Base training. Showcase images :<ul><li>Euler / normal / 20 steps / CFG 5</li><li>Hires steps : 20 / NMKD_SIAX @0.2-0.5 / x1.5-x2</li><li>768x1152</li><li>Lora strength 0.7 -1</li></ul><h3 id="qwen">Qwen</h3>Qwen2512 v1:First lora trained on the new Qwen2512 (it still working with previous Qwen-Image and Qwen-Edit). For inference, I still prefer the first Qwen-Image model (BF16) (all the showcase images are done with this one).Seems pretty good but few things appears sometimes unprompted in my tests: artefacts on skin (like scars) and japanese onomatopoeia Qwen v1:I've trained a lot of different versions for this one : with big and small dataset, trigger words or not, high and low LR... I've still no idea what's good or not. 🙂 <h3 id="flux">Flux</h3>Had good results starting prompt with : 'black and white Berserk manga style image of'and 0.8 strength most of the time v2 edit : Better dataset for better prompt adherence and flexibility

Manga style (Berserk)

berserk_id4.safetensors

Ideogram4 v1

Krea2 v1

Klein 9B v1

ZIB v1

Qwen2512 v1

Qwen v1

Flux v2

Flux v1

Files with SHA256: 3c9b7cd92b6b4073c85ba5196d9edf79f6ee7eecc84c1bc669f6ff4e8b79fb41