NSFW

pasanctuarySDXL_v10.safetensors

6.62 GB · SafeTensor · fp16 · pruned

sdxl_vae.safetensors

319 MB · SafeTensor

<pasanctuary-xl>

This is my flagship PaSanctuary (SDXL, IllustriousXL). I find it's in line with what the community on Civitai likes producing. It's pretty versatile while also having an artstyle that's unique in image generation. NSFW compatible. Check out my other Checkpoints. Refer to the version details for Changelog. V5: This Checkpoint is trained on the awesome Basemodel . The only prompt you ever need is this positive prompt: masterpiece, best quality, newest, absurdres, highres Default negative Prompt: worst quality, old, early, low quality, lowres, bad hands, mutated hands, greyscale Additional option for Style change are: - realistic No need for any additional negatives. Anything else for tag related stuff, see Basemodel . This model is designed to work with resources trained on NoobAI-XL V1.1. Other SDXL or pony resources may not work. I also recommend to use the Extension . Settings for generating Images for V5: - Sampler: Euler a - Steps: 30 - CFG 6.0 - Base Resolution 1024x1024 Recipe: Merge to Checkpoint: TCV Style LoRA Restart Illustrious-XL + . No additional Merge with block weights, adjustment and clip/tenc. V4: This Checkpoint is trained on the awesome Basemodel . The only prompt you ever need is this positive prompt: masterpiece, best quality, newest, absurdres, highres Default negative Prompt: worst quality, old, early, low quality, lowres, bad hands, mutated hands, greyscale Additional option for Style change are: - realistic/ 3d No need for any additional negatives, except realistic, 3d, if the realism is bleeding in. Putting 3d in negative prompt is mostly enough. Anything else for tag related stuff, see Basemodel . This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work. I also recommend to use the Extension . Settings for generating Images for V4: - Sampler: Euler a - Steps: 24-30 - CFG 5.0-6.0 - Base Resolution 1024x1024 If you have the Option, i would recommend this for Realism: - Sampler: Restart - Scheduler type: SGM Uniform - Steps: 16-18 - CFG 6.0 - Base Resolution 1024x1024 Recipe: Merge to Checkpoint: on Weight 0.6 + on Weight 0.3 + from on Weight 0.4 + . No additional Merge with block weights, adjustment and clip/tenc. V3: This Checkpoint is trained on the awesome Basemodel . The only prompt you ever need is this positive prompt: masterpiece, best quality Default negative Prompt: lowres, worst quality, low quality, bad anatomy, bad proportions, simple background, Additional option for Style change are: - realistic/ 3d No need for any additional negatives, except realistic, 3d, if the realism is bleeding in. Putting 3d in negative prompt is mostly enough. Anything else for tag related stuff, see Basemodel . This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work. I also recommend to use the Extension . Settings for generating Images for V3: - Sampler: Euler a - Steps: 24 - CFG 6.0 - Base Resolution 1024x1024 If you have the Option, i would recommend this: - Sampler: Restart - Scheduler type: SGM Uniform - Steps: 16-18 - CFG 6.0 - Base Resolution 1024x1024 Recipe: Checkpoint Merge: PaSanctuary v2.5 (38%) + Nooabi v1.0 Epsilon (62%) Merge to Checkpoint: on Weight 0.8 + from on Weight 0.55. Replaced CLIP G and CLIP L from and merged into Checkpoint. V2.5: This Checkpoint is trained on the awesome Basemodel . The only prompt you ever need is this positive prompt: masterpiece, best quality Default negative Prompt: lowres, worst quality, low quality, bad anatomy, bad proportions, extra limbs, extra digit, extra legs, extra legs and arms, disfigured, missing arms, too many fingers, fused fingers, missing fingers, unclear eyes, username, simple background, Anything else for tag related stuff, see Basemodel . This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work. I also recommend to use the Extension . Settings for generating Images for V2.5: - Sampler: Euler a - Steps: 24 - CFG 6.0 - Base Resolution 1024x1024 If you have the Option, i would recommend this: - Sampler: Restart - Scheduler type: SGM Uniform - Steps: 16-18 - CFG 6.0 - Base Resolution 1024x1024 Recipe: Merge to Checkpoint: on Weight 1.0 + from on Weight 1.0 + . No additional Merge with block weights, adjustment and clip/tenc. This ckpt is now under Fair-AI-Public-License-1.0-SD. V2: This Checkpoint is trained on the awesome Basemodel . The only prompt you ever need is this positive prompt: masterpiece, best quality Additional option for Style change are: - anime - realistic Default negative Prompt: lowres, worst quality, low quality, bad anatomy, bad proportions, extra limbs, extra digit, extra legs, extra legs and arms, disfigured, missing arms, too many fingers, fused fingers, missing fingers, unclear eyes, username, simple background, No need for any additional negatives, except realistic, 3d, if the realism is bleeding in, despite prompting anime. Anything else for tag related stuff, see Basemodel . This model is designed to work with resources trained on Illustrious-XL-v0.1. Other SDXL or pony resources may not work. I also recommend to use the Extension . Settings for generating Images for V2: - Sampler: Euler a - Steps: 24 - CFG 6.0 - Base Resolution 1024x1024 Recipe: Merge to Checkpoint: on Weight 1.0 + . No additional Merge with block weights and adjustment. This ckpt is now under Fair-AI-Public-License-1.0-SD. V1: This Checkpoint is trained on the awesome Basemodel . This is in Collaboration with Check out his 😉 The only prompt you ever need is this positive prompt: masterpiece, best quality Default negtive Prompt: lowres, worst quality, low quality, bad anatomy, bad hands, 4koma, comic, greyscale, jpeg artifacts, overly saturated, overly vivid No need for any additional negatives, except realistic,

SHA256

6D404D5AC07D43D9922538A155405211935FB775DA8D3EDE2C524518748D822B

ID de modelo de ModelTrends.ai

#13415

Sampler

Euler a

Pasos

24

Guidance

6

Semilla

2365893133

Tamaño

832x1216

Sampler

Euler a

Pasos

24

Guidance

6

Semilla

1579997726

Tamaño

832x1216

Sampler

Euler a

Pasos

28

Guidance

6

Semilla

2992048740

Tamaño

832x1216

Sampler

Euler a

Pasos

24

Guidance

6

Semilla

1598313338

Tamaño

832x1216

Sampler

Euler a

Pasos

24

Guidance

6

Semilla

2368482009

Tamaño

832x1216

Sampler

Euler a

Pasos

24

Guidance

7

Semilla

92068827

Tamaño

832x1216

Sampler

Euler a

Pasos

24

Guidance

6

Semilla

3389772577

Tamaño

832x1216

Sampler

Euler a

Pasos

24

Guidance

6

Semilla

1585408606

Tamaño

832x1216

Heat score

One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.

Floor

The 7,000° every model with real data starts from. Numbers below it are stand-ins for models without data.

Download-equivalents

Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.

Log scale

Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.

Likes

Thumbs up and likes from every source, worth half a download each on the log scale.

Download speed

How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.

Measured and estimated

Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.

Seeder

Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.

AI Horde

A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.

Generation sites

Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.

Graydient runs

How often a model has been run on Graydient, counted like downloads.

Full model (checkpoint)

The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.

LoRA and embedding

Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.

Family and weights

The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.

Age of the weights

Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.

Family boost

A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.

Stand-in score

A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.

Trend

How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.

Typical model

The middle of the catalog: half the models with a figure grew faster over the period, half slower.