<h1 id="luma">🌕 LUMA Experimental Edition</h1>This is Luma-based semi-realistic checkpoint, finetuned experimentally with different datasets, ways of captioning and training parameters. Please note, that it can be incompatible with some of Loras on high weights and may produce some overburns.<h3 id="heading-536">Model1: Luma DEv4 - finetuned with some images and prompts from Dall-E 3.</h3>I highly recommend to use short and meaningful tags in your prompts. You may see some examples in sample images. Also this model is very flexible, so you may add some extra styles (like anime, oil painting, flat color, cartoon, etc.) for better variations.All the content I make is and will be completely free on CivitAI. But if you want to support me with a coin, then <a target="_blank" rel="ugc" href="https://boosty.to/sadxzero/donate">you can do it here</a>.<h2 id="usage">Usage</h2>Recommended embeddings: 1. <a target="_blank" rel="ugc" href="https://civarchive.com/models/7808/easynegative">easynegative</a> 2. <a target="_blank" rel="ugc" href="https://huggingface.co/gsdf/Counterfeit-V3.0/blob/main/embedding/EasyNegativeV2.safetensors">easynegativev2</a> 3. <a target="_blank" rel="ugc" href="https://cdn.discordapp.com/attachments/1032948846197747731/1069660323709190195/bad-hands-5.pt">bad-hands-5</a> 4. <a target="_blank" rel="ugc" href="https://civarchive.com/models/16993/badhandv4-animeillustdiffusion">badhandv4</a>Recommended extensions: 1. <a target="_blank" rel="ugc" href="https://civarchive.com/models/95923?modelVersionId=102438">AutoChar</a> 2. <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">AfterDetailer</a><h3 id="my-regular-settings">My regular settings:</h3>Clip Skip 2 Necessary negative prompt: <a target="_blank" rel="ugc" href="https://civarchive.com/models/7808/easynegative">easynegative </a>or <a target="_blank" rel="ugc" href="https://huggingface.co/gsdf/Counterfeit-V3.0/blob/main/embedding/EasyNegativeV2.safetensors">easynegativev2</a> VAE: vae-ft-mse-840000 Sampler: any ENSD: 31337 Hires.fix: x1.5 and higher Upscaler: Option 1: 8x_NMKD-Superscale_150000_G for realism or R-ESRGAN 4x+ Anime6B for illustrations (Denoising strenght 0.3-0.5) Option 2: Latent (any) or Lanczos (Denoising strength 0.5-0.6) Never use Face Restoration! If you want better faces just use <a target="_blank" rel="ugc" href="https://github.com/alexv0iceh/AutoChar">AutoChar</a> or <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">AfterDetailer.</a>But you may feel free to experiment.

SXZ Luma Experimental

Finetuned with pics and promts from Dall-E 3 via Bing Image Creator. Mostly trained in text encoder part. Very flexible, but sometimes may produce artifacts with Lora's on high values.

Files with SHA256: b524aaf90cc771cdc219440b96723e4a1a3f03f8cfc7a8eaff91cd18995a1b37