<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/beeffe59-dafd-4af8-8b39-522dbd472dee/width=525/beeffe59-dafd-4af8-8b39-522dbd472dee.jpeg" />there is a non-lightning version available above.This is an early version of an Anime model I have been working on lately that finally got to a starting point. Trying to fuse the darkpizza oldschool Japanime look with some modern anime looks. It's missing some concepts and cohesion still, but this is a start. All cover images are random prompts thrown at it with basic adetailer. Yes, the hands somewhat suck lol. Please use the embedded VAE. This is put together for simple text prompts that turn out heavily stylized. You will need external control of some kind if you try to get very intricate with it. The NL version is more generic and may be better for traditional works. Just try em out. This is mainy for me, I shared it because I liked where it is heading.~This still needs face detailer currently for eyes, nothing aggressive.~Settings:CFG: 1-2Steps 4+ (5)Sampler: dpmpp_sde_gpuScheduler: karrasDenoise: 1.0Noise mode: GPUNL version should be fine around 20 steps and 6.5CFG at the same settings.Negatives:Whatever you need, here is an artsy one.~embedding:unaestheticXL_hk1, hat, (low quality, worst quality:1.2), (grayscale, grainy, border), (watermark:1.2)on-site generation is available<a target="_blank" rel="ugc" href="https://tensor.art/u/625051474237359203"> here.</a><a target="_blank" rel="ugc" href="https://ko-fi.com/marduk191">Tip Jar</a>Discord: <a target="_blank" rel="ugc" href="https://discord.gg/btCfTh4jgt">https://discord.gg/btCfTh4jgt</a>

marduk191's Pseudo-Modern Anime (lightning)

v1:DarkPizza Origin v3.0, DuplicationXL V1.0, VooDoo, aamXLAnimeMix v1.0, Lightning, XL_VAE_C A little extra training to offset some styles, merged a couple of trained loras, WIP

marduk191sPseudoModern_v10.safetensors

v1.0

v1.0- NL

This is an early beta version of an Anime model I have been working on lately. Trying to fuse the darkpizza oldschool Japanime look with some modern anime looks. It's missing some concepts and cohesion still, but this is a start so people can try it out and give some feedback. Feel free to send lora patches and comfy merge workflow patches, I'll look at them as long as you have a description of what it should be doing.This includes more oldschool style clip data at clip skip 1 and more modern natural language at clip skip 2.This still needs face detailer currently for eyes, nothing aggressive.Settings:CFG: 1-2Steps 4+ (5)Sampler: dpmpp_sde_gpuScheduler: karrasDenoise: 1.0Noise mode: GPUNegatives:Whatever you need, here is an artsy one.~embedding:unaestheticXL_hk1, hat, (low quality, worst quality:1.2), (grayscale, grainy, border), (watermark:1.2)

Files with SHA256: 8a44dcfc8fc6ce7bc333c3e26ee5475fc06b18475af461fd9cdd7d2d77dcadbc