【CHECKPOINT】Hassaku (hentai model无尽模型）hassakuHentaiModel_v11[973CB455D0]

名称：hassakuHentaiModel_v11.safetensors
类型：【CHECKPOINT MERGE】
特性标签：CHARACTER、ANIME
程序版本：SD 1.5
模型大小：1.99GB
概述：
Use mostly danbooru tags. No extra vae needed. For better promting on it, use this LINK or LINK. But instead of {}, use (), stable-diffusion-webui use (). Use "masterpiece" and "best quality" in positive, "worst quality" and "low quality" in negative.
My negative ones are: (low quality, worst quality:1.4) with extra monochrome, signature, text or logo when needed.
Use a clip skip 1 or 2. Clip 2 is better for private parts, img2img and prompt following. Clip 1 is visually better, because i assume, the model has more time and freedom there. I use clip2.
Don't use face restore and underscores _, type red eyes and not red_eyes.
Don't go to really high resolutions. Every model, like hassaku, get lost in the vastness of big images and has a much higher chance to greate, as example, a second anus.
Loras:
Every LoRA that is build to function on anyV3 or orangeMixes, works on hassaku too. Some can be found here, here or on civit by lottalewds, Trauter, Your_computer, ekune or lykon.
Base model for hassaku where AnythingV3, ElysiumV2, AbyssOrangeMix, a bit of AbyssOrangeMix2, basilMix.
Black result fix (vae bug in web ui): Use --no-half-vae in your command line arguments
主要使用丹布鲁标签。无需额外的 VA。为了更好地使用它，请使用此链接或链接。但是，使用（），而不是{}，使用stable-diffusion-webui use（）。正面使用“杰作”和“最佳质量”，负面使用“最差质量”和“低质量”。
我的缺点是：（低质量，最差质量：1.4）在需要时带有额外的单色，签名，文本或徽标。
使用剪辑跳过 1 或 2。剪辑 2 更适合、img2img 和提示跟随。剪辑 1 在视觉上更好，因为我认为模型在那里有更多的时间和自由。我使用剪辑2。
不要使用面部恢复和下划线_，输入红眼睛而不是red_eyes。
不要使用非常高的分辨率。每个模特，如 hassaku，都会迷失在浩瀚的大图像中，并且有更高的机会放大，例如第二个肛门。
洛拉斯：
每个构建为在anyV3或orangeMixes上运行的LoRA，也适用于hassaku。有些可以在这里，这里或由lottalewds，Trauter，Your_computer，ekune或lykon找到。
hassaku的基本模型，其中AnythingV3，ElysiumV2，AbyssOrangeMix，一点AbyssOrangeMix2，basilMix。
黑色结果修复（Web UI 中的 vae 错误）：在命令行参数中使用 --no-half-vae
我使用 Eta 噪声种子增量 31337 或 0，对于示例图像，剪辑跳过为 2。模型质量主要通过采样器DDIM和DPM++ SDE Karras证明。我最喜欢DDIM（因为它是最快的）

Hash	parameter
SHA256	973CB455D05021017B8B650EC36ABF5A0A5D5C7BD05C76796F650BE72F9E3B87
CRC32	605BDC64
BLAKE3	CB2EC18407C454B72C68E64E9F583A60EF98A9F3B434A5C5E2A407A408A58CAD
AUTOV1	0FD91EF7
AUTOV2	973CB455D0

作品展示：

Generation Data：

1. masterpiece, best quality, 1girl, red eyes, white hair, mechanical legs, raincoat, black gloves, black coat, raining, sky, ruins, rifle, headset, rubble, android, long hair, halo,
   
2. Negative prompt: (worst quality, low quality:1.4),
   
3. ENSD: 31337, Size: 512x704, Seed: 1793726502, Steps: 20, Sampler: DDIM, CFG scale: 7, Clip skip: 2, Model hash: 973cb455d0, Hires steps: 20, Hires upscale: 1.5, Hires upscaler: Latent (nearest-exact), Denoising strength: 0.46

复制代码

Generation Data：

1. masterpiece, best quality, 1girl, (space), spacecraft, (spacesuit), upper body, from side, science fiction, yellow eyes, twintails, silver hair, cat ears, looking at viewer,
   
2. Negative prompt: (worst quality, low quality:1.4),
   
3. ENSD: 31337, Size: 512x640, Seed: 2589211749, Steps: 20, Sampler: DDIM, CFG scale: 7, Clip skip: 2, Model hash: 973cb455d0, Hires steps: 20, Hires upscale: 1.9, Hires upscaler: Latent (nearest-exact), Denoising strength: 0.5

复制代码

Generation Data：

1. 1girl, blue_rose, blue_flower, flower, hair_ornament, jewelry, dress, solo, hair_flower, short_hair, necklace, rose, earrings, blush, silver_hair, bare_shoulders,<lora:furano:0.5>, masterpiece, best quality,
   
2. Negative prompt: EasyNegative,nswf, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
   
3. ENSD: 31337, Size: 512x360, Seed: 4024959879, Model: hassakuHentaiModel_v11, Steps: 20, Sampler: DPM++ 2S a Karras, CFG scale: 7, Clip skip: 2, Model hash: 973cb455d0

复制代码

Generation Data：

1. (a simplistic sketch of a girl sitting on the floor, she is spacing out and looking upwards, =), ((masterpiece:1.2, best quality)), 1lady, solo, black hair, black eyes, oversized clothes, (white shirt), simple lines, (white background), necklace, dark eyes, uninterested, looking away, facing away, bare thighs, bare shoulders,
   
2. Negative prompt: (worst quality, low quality:1.4), multiple views, blurry, multiple panels, watermark, letterbox, text,
   
3. bad-hands-5 badhandv4 bad_prompt_version2 EasyNegative ng_deepnegative_v1_75t verybadimagenegative_v1.3
   
4. VAE: orangemix.vae, ENSD: 31337, Size: 512x768, Seed: 1073381774, Model: hassakuHentaiModel_v11, Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Clip skip: 1, Model hash: 973cb455d0, Hires upscale: 2, Hires upscaler: Latent, Denoising strength: 0.7, Token merging ratio hr: 0.5

复制代码

Generation Data：

1. gotou1, gotou hitori, solo, pink jacket, track jacket, bangs, hair between eyes, long sleeves,
   
2. Negative prompt: EasyNegative
   
3. ENSD: 9199919, Size: 512x696, Seed: 2026632685, Model: hassakuHentaiModel_v11, Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Clip skip: 2, Model hash: 973cb455d0, Hires upscale: 1.7, AddNet Enabled: True, AddNet Model 1: gotohHitoriBocchiThe_v10(1757182f367d), AddNet Model 2: crazyExpressions_crazyExpressions(3837e43b4976), Hires upscaler: Latent, AddNet Module 1: LoRA, AddNet Module 2: LoRA, AddNet Weight A 1: 0.6, AddNet Weight A 2: 0.7, AddNet Weight B 1: 0.6, AddNet Weight B 2: 0.7, Denoising strength: 0.55

复制代码

下载地址：

游客，如果您要查看本帖隐藏内容请回复

666牛啊牛啊