If you enjoy my work, please give me a "like" rating; it means a lot to me!<a target="_blank" rel="ugc" href="https://civarchive.com/user/vjleoliu">Check out other creations here</a>I don't speak English, but I wrote the explanation very carefully. It won't take more than two minutes to read. The following translation is from ChatGPT.<h1 id="portray_v1.0-up7bmpc7q">《Portray_v1.0》</h1>This may be the best SD1.5 realistic large-scale model so far (for me).<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bfa61818-7473-47f3-b4db-d554207d6549/width=525/bfa61818-7473-47f3-b4db-d554207d6549.jpeg" />Have you ever thought about using an SD1.5 model to simulate the output quality of SDXL? I believe this model has achieved this to a certain extent. At least in the numerous image tests I conducted, the vast majority of feedback thought it was produced by SDXL, but in fact, it was SD1.5. This means it will render images at a faster speed.It has great potential waiting for you to explore.<h3 id="feature-bgksr0saf">feature</h3><ol><li>The fashion shots have rich and smoky colors, with customizable color themes. The example images are four that were produced in one go, without special embellishment, and they are basically at a usable level with a high success rate for the final images.The facial features have been optimized, so you no longer need to worry about "AI faces" . If you want to asian thing, add the prompt "asian aesthetics".</li><li><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/70a2421a-5896-48d6-97ac-cc390010d516/width=525/70a2421a-5896-48d6-97ac-cc390010d516.jpeg" />Film-like images can simulate extreme changes in light and shadow, producing results close to the effects of a Leica camera. It has a high degree of realism in reproducing natural effects such as water, fire, and smoke. <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f1679a17-6c34-4bf4-9aff-fa089d7938a4/width=525/f1679a17-6c34-4bf4-9aff-fa089d7938a4.jpeg" /></li><li>It supports multiple artistic styles triggered by artistic forms or the names of artists.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/078b6db7-80d9-4235-a123-08b3acfaa50e/width=525/078b6db7-80d9-4235-a123-08b3acfaa50e.jpeg" /></li><li>It possesses a certain level of design comprehension, with examples such as poster design.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5345bb50-7fa0-4d7d-bb75-cce6a27a6990/width=525/5345bb50-7fa0-4d7d-bb75-cce6a27a6990.jpeg" /></li><li>It enhances support for natural language, allowing the use of long text similar to SDXL as prompt words, directly copying the XL homework.</li><li>Integrated the highly praised 《SDXLrender》, <a target="_blank" rel="ugc" href="https://civarchive.com/models/171159">link</a></li></ol><h3 id="recommended-settings-ss2qpue13">Recommended Settings</h3>Steps: 30Sampler: Euler a, Schedule type: AutomaticCFG scale: 6Size: 512x768<h3 id="upscale-setting-m9so0eog6">Upscale setting</h3>The recommended sampling method is Euler A, other sampling methods are still pending testing.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5c5bf6c6-2b47-4534-8bff-4f26a83e1156/width=525/5c5bf6c6-2b47-4534-8bff-4f26a83e1156.jpeg" />The recommended model for upscaling is 4x_NMKD-Siax_200k / high-resolution iteration steps 9 to 18 / redrawing amplitude 0.3 to 0.6, with the first upscaling for picture refinement and the second for sharpness gain.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b7b57508-7394-4bd1-b3a5-8ca514163dba/width=525/b7b57508-7394-4bd1-b3a5-8ca514163dba.jpeg" /><h3 id="ok-that's-all-f3wda03bm">OK, that's all</h3>If you enjoy my work, please give me a "like" rating; it means a lot to me!<a target="_blank" rel="ugc" href="https://civarchive.com/user/vjleoliu">Check out other creations here</a><h2 id="i-hope-you-have-funpeace-hbkst8vj0">I hope you have fun！Peace！</h2>

Portray

Negative prompt: nsfw, nipples, text, worst quality, low quality, deformed iris, bad pupils, morbid, mutilated, poorly drawn face, cross-eyed, deformed, bad anatomy, bad proportions, extra limbs, disfigured

portray_v10.safetensors

v1.0

Unbounded_LCM

"UNENDING_v1.0"
It may be the best SD1.5 realistic large model you have seen so far (for me).
Why do I say that?
I don't know if you have ever thought tha* ***ng an SD1.5 model to simulate the output quality of SDXL, I think this model has achieved it to a certain extent. At least in the extensive image tests I have conducted, the vast majority of feedback thought it was produced by SDXL, but in fact it is SD1.5, which means it will render images faster.
It has great potential waiting for you to explore.
 
Its advantages:
1. Say goodbye to the same AI faces
2. Simulation of a single-lens reflex camera, to be more precise, it is more like a Leica camera.
3. Better support for natural language
4. Integrated well-received SDXLrender, <a href="https://www.liblib.art/modelinfo/6f5e32f6458e4391b1bbb941ff0a4c3b" target="_blank">link</a>
 
Recommended settings:
1. The recommended sampling method is Euler a, especially when zooming in. Using other sampling methods may not yield good results.
2. If the face effect of a bust or full-body portrait is not good, please use Hires. fix, recommended redraw range 0.3~0.6. Enlarging the picture once will give you a perfect result, enlarging it twice will make the picture very sharp.
3. If you want to get an Asian face, just add "asian aesthetics" in the prompt.
4. For more tips on usage, feel free to join the AI mutual assistance group, let's explore together. Q group number: 482570609

Files with SHA256: 79316b73b46ba99f98a3a1f218505a771ebf3faf06da85e1dce75d657f236578