The Boops版本UberBoop.fp16 (ID: 591853)

As requested, here is the collection of "boop"-related merges I've been using over the past few months. I'll list them out here and then for each version, I'll put its description there, as well as well as each model's example images.

• ~boop

  • merge of analogMadness_v60, and aZovyaPhotoreal_v2

  • The first attempt at a photorealistic merged checkpoint and, honestly, it works pretty well.

  • It handles prompts fairly well, and like later versions, I use mainly "Euler a" or "DPM++ 2M SDE - Kerras."

  • For guidance, I generally use between 4 and 6, and sampling steps from 20 to 29.

  • I almost always use Beyondv4-neg and bad-hands-5 in the negative prompts.

  • It will produce SFW & NSFW images and does people pretty well and handles a fairly large number of descriptors and/or loras before image quality suffers.

• ~boopV2-inpainting

  • merge of pornmasterPro_fullV5-inpainting, and ~boop

  • This is included mostly for completeness. In a mad scientist kind of scenario, I tried to incorporate an inpainting model into a standard SD15 model.

  • While it will produce images, they always are a bit muted, color-wise, and usually generate with a weird red border.

  • There are reasons I don't use this one. Unless you're looking for muted colors and odd borders, I would use any of the other models.

  • It handles prompts fairly well, and like later versions, I use mainly "Euler a" or "DPM++ 2M SDE - Kerras."

  • For guidance, I generally use between 4 and 6, and sampling steps from 20 to 29.

  • I almost always use Beyondv4-neg and bad-hands-5 in the negative prompts.

  • It will produce SFW & NSFW images and does people pretty well and handles a fairly small number of descriptors and/or loras before image quality suffers.

• ~boopv3

  • merge of serenity_v10Safetensors, and ~boop

  • The 3rd attempt at a merge with which I was happy, this is one that I have used for a while, now, right up until I decided PhotoBoopV4 worked in a satisfactory manner.

  • It handles prompts pretty well, and like later versions, I use mainly "Euler a" or "DPM++ 2M SDE - Kerras."

  • For guidance, I generally use between 4 and 6, and sampling steps from 20 to 29.

  • I almost always use Beyondv4-neg and bad-hands-5 in the negative prompts.

  • It will produce SFW & NSFW images and does people pretty well and handles a fairly large number of descriptors and/or loras before image quality suffers.

• boopXL

  • merge of photoMovie_photoMovieSXL, Photo Movie SX.fp16, and ~boopv3

  • Another "mad scientist" attempt, this time to shove SDXL and SD15 into the same mold as sort of a "do everything" merge.

  • However, like a lot of mad scientist experiments, this has flaws.

  • The main flaw, however, is a biggie, to me. It doesn't really pay a lot of attention to the prompt.

  • You will get a lot of "the spirit of the prompt" rather than "the letter of the prompt." I haven't found one that really gives me what I prompted for.

• PhotoBoopV4

  • merge of ~boopv3, and photon_v1

  • The 4th iteration, or attempt, at a merged checkpoint that was more what I was looking for.

  • Prompt processing is mixed. "Euler a" is usually the closest to the prompt, though I generally like the output using "DPM++ 2M SDE - Kerras" better.

  • For guidance, I generally use between 4 and 6, and sampling steps from 20 to 29.

  • I almost always use Beyondv4-neg and bad-hands-5 in the negative prompts.

  • It will produce SFW & NSFW images.

• BoopV4.fp16

  • merge of ~boopv3, and photon_v1

  • A fp16 version of PhotoBoopV4.

  • It behaves much like PhotoBoopV4, so, as stated below, prompt processing is mixed. "Euler a" is usually the closest to the prompt, though I generally like the output using "DPM++ 2M SDE - Kerras" better.

  • For guidance, I generally use between 4 and 6, and sampling steps from 20 to 29.

  • I almost always use Beyondv4-neg and bad-hands-5 in the negative prompts.

  • It will produce SFW & NSFW images.

描述:

Merge of BoopV4.fp16 (0.25) + absolutereality_v181 (0.5) + epicrealism_naturalSinRC1VAE (0.25)

A new merge based off of PhotoBoop.fp16 (obviously)

I'm currently hitting it with a lot of test images and, for the most part, things look good.

For guidance, I generally use between 4 and 6, and sampling steps from 20 to 29.

I almost always use Beyondv4-neg and bad-hands-5 in the negative prompts.

It will produce SFW & NSFW images.

• DDIM is consistent across schedule types

• DPM adaptive is consistent across schedule types but isn't the best at sticking to the prompt.

• DPM fast is not recommended unless you like really trippy and fairly bad generations...

• DPM++ 2M works well with Karras, Exponential, and Polyexponential; Uniform and SGM Uniform give you roughly the same image just with more burn and splotchiness.

• DPM++ 2M SDE works well with Karras but is a bit iffy with the others, Exp and Poly sometimes give decent results with U & SGM U being quality-free for your convenience.

• DPM++ 2M SDE Heun is iffy across the board with Karraws and Exp probably giving the most usable output

• DPM++ 2M Sa has better quality with Karras with Exp being a close second. Poly seems to go its own way with Loras at 0.85 in potentially good but unpredictable output. I don't know why... U and SGM U are iffy at best.

• DPM++ 3M is your fast path to awful output.

• DPM++ SDE has decent output across the schedule types but has a predilection for meandering off the prompt path.

• DPM2 behaves pretty well using Karras or Poly, but the rest leave a lot to be desired.

• DPM2a is a bit of a crapshoot across the board, which is to say that the results are unpredictable and not the best quality.

• Euler is acceptable and fairly consistent across schedule types.

• Euler A is unpredictable and will sometimes give you amazing results -- just not what you were expecting.

• Heun gives acceptable and fairly consistent output across schedule types.

• LCM is great for images you don't want to be either what you want or of a decent quality. It made some completely messed up and kind of dark -- in a horror kind of way. I'm not sure I recommend it.

• LMS is unusable with U and SGM U schedule types while the others will give occasionally good output.

• PLMS ... just... no. Weirdly, it output really nice output for the gecko prompt. Everything else was hot garbage.

• Restart does well with all the schedule types except SGM Uniform. Those get weird.

• UniPC is another it's best to just avoid.

训练词语: