<h1 id="for-flux-2gyng07lq">For Flux</h1>All images I experimented on ComfyUI. You can just simply use my images for nodes and workflows.<h3 id="parameters-and-guides:-t3phz67kf">Parameters &amp; guides:</h3>Here are models that I used: flux-1dev, fp8_e4m3fn, t5xxl_fp16, and the original vae Flux<ul><li>Use Flux sentence-style prompts</li><li>no trigger words required</li></ul><ul><li>Lora weight: 0.95</li><li>scheduler: Euler with dpmpp_2m</li><li>for DualClipLoader: only place prompts in t5xxl box and leave clip_1 empty</li><li>max_shift: 1.15</li><li>base_shift: 0.50</li><li>Steps: 25 or 50</li><li>denoise: 1.00</li><li>guidance: 3.5</li></ul>Share your creations here and give some suggestions for whom you'd like me to make a LoRA model of.<hr /><h1 id="for-pony-qapwxbqow">for Pony</h1>All images I experimented on A1111. You can just put my images on "PNG Info" on A1111 or any preferred tools.<h3 id="suggested-parameters-and-guides:-encg256px">Suggested Parameters &amp; guides:</h3><ul><li>Use any pony model, but I suggest using DucHaiten-Pony-RealV1.1 and CyberrealisticPony_v63.</li><li>Trigger words:<ul><li>No trigger words required. However, try adding "Chinese" in person prompt such as "teenager" &gt;&gt; "Korean teenager" can sometimes boost lora.</li></ul></li></ul><ul><li>Lora weight:<ul><li>best at 0.10-1.00</li></ul></li><li>Sampler:<ul><li>DPM++ SDE Karras or Euler a</li></ul></li><li>Resolution: 832x1216</li><li>Steps: 18 - 30</li></ul>Enjoy!

[DW] Digital Warlock - Chinese Doll Likeliness - Flux + Pony

All images I experimented on ComfyUI. You can just simply use my images for nodes and workflows.Parameters &amp; guides:Here are models that I used: flux-1dev, fp8_e4m3fn, t5xxl_fp16, and the original vae Flux<ul><li>Use Flux sentence-style prompts</li><li>no trigger words required</li></ul><ul><li>Lora weight: 0.95</li><li>scheduler: Euler with dpmpp_2m</li><li>for DualClipLoader: only place prompts in t5xxl box and leave clip_1 empty</li><li>max_shift: 1.15</li><li>base_shift: 0.50</li><li>Steps: 25 or 50</li><li>denoise: 1.00</li><li>guidance: 3.5</li></ul>Share your creations here and give some suggestions for whom you'd like me to make a LoRA model of.

Files with SHA256: bd53bfde51ccc045424d9120af160ad8bf3f5f6e7a547b37d04b1d6c4527b5b6