Please read through the entire description (might need to be expanded) and the version change notes as they cover a lot of information about basic use cases and limitations. The description is always focused on the latest version. Thank you!This is an SD 1.5 LoRA for the character Dawn / Hikari from Pokemon. It works for models based on SD 1.x only, it will not work for models based on SD 2.x or SDXL!Example images were picked from base resolution txt2img results + the FreeU extension (<a target="_blank" rel="ugc" href="https://github.com/ljleb/sd-webui-freeu">https://github.com/ljleb/sd-webui-freeu</a>) enabled with default settings to further improve results (see last example images for a comparison of FreeU disabled vs enabled). They were then re-created at 2x resolutions using txt2img with moderate Hi-res Fix settings (upscaler Lanczos, denoising strength 0.4). This improves faces and other details that are almost impossible to get correctly and consistently at base resolutions (limitation of the technology) while still giving a realistic impression of what it looks like. Base resolution results will have more distorted faces and less detail.Please see the version change notes for the training and example image generation models as well as the used weights as they might change between versions. Remember that you might need to adjust weights to best suit your use case!Remember to add the tag dawn \(pokemon\) (with backslashes intact) to your positive prompt.The training set contained multiple variations of Dawn's signature look (not including alternate outfits for now, sorry) so you might need to put combinations of the following tags in your positive or negative prompts to get the desired results:<ul><li>beanie</li><li>bracelet</li><li>duffel bag</li><li>hairclip</li><li>knee boots</li><li>kneehighs</li><li>poketch</li><li>scarf</li><li>skirt</li><li>sleeveless shirt</li></ul>As the training set also contained a few images with floating bits, you might need to add the negative prompts floating hair and/or floating scarf if not desired.Known Limitations / Problems:<ul><li>The bag and boots were not present in a lot of images and not a focus for the training so they sadly will not be consistent at all.</li><li>Same goes for the bracelet and poketch but they might be a bit more recognizable from time to time.</li><li>The beanie pattern needs a bit of luck to get correctly (sadly seems very difficult to train correctly).</li><li>Eyes and hair had different colors (blue and black) in the training data, better to specify explicitly.</li><li>You might also need to prompt for specific clothing colors from time to time, don't really know why yet.</li><li>Depending on the clothing, framing etc. it may be more or less difficult to remove the beanie. I recommend a negative prompt with additional weight as well as specifying a hair color, e.g. blue hair in the positive prompts which seems to help. Still, that beanie (especially its pattern) really wants to be there.</li><li>The kneehighs might sometimes result in two parts, the kneehighs themselves and a separate part at the thighs, leaving the knee exposed. No idea what causes that, it might help to put thighhighs or clothing cutout in the negative prompts.</li></ul>

[SD 1.5] Pokemon - Dawn / Hikari

There are detailed changes below the next paragraph, you might need to expand this version changes box!I learned a few new things about creating LoRAs and wanted to see how far I can push my existing LoRAs without changes to their datasets. So there's still no support for alternate outfits, colors etc. for now, sorry! There are other LoRAs if you want those things. Not sure if I'll improve the LoRAs more than that in the future or make new ones but who knows.LoRA Changes:<ul><li>Now uses the standard "dawn \(pokemon\)" instead of a custom trigger word to make things easier for everyone (please note though that the LoRA itself is still named "character_pokemon_dawn_vX" as before!)</li><li>Switch to 32 dims (now trained directly instead of resizing from 128)</li><li>Switch to target weight 1 (increased from 0.7)</li><li>Changed a lot of training settings (too many to list, check LoRA metadata if you are interested) and updated to much newer scripts version (~3 months worth of changes)</li></ul>Example image changes:<ul><li>Use CLIP skip 2 instead of 1 as I accidentally did before</li><li>Change settings for hir-res fix: Switch upscaler from None to Lanczos and increase denoise from 0.1 to 0.4 to get better results while still not changing TOO much</li><li>Use a negative embedding for the majority of negative prompting</li></ul>Recommended weight: 1Training model: <a target="_blank" rel="ugc" href="https://civitai.com/models/66/anything-v3">Anything V3</a>Example image generation model: <a target="_blank" rel="ugc" href="https://civitai.com/models/4451/abyssorangemix2-hardcore">AbyssOrangeMix2 - Hardcore</a>

character_pokemon_dawn_v6.safetensors

Autor: a9408020a989Link: https://civitai.com/models/9100?modelVersionId=99550DetailsTypeLORADownloads744UploadedJun 19, 2023Base ModelSD 1.5Trigger WordsDAWN \(POKEMON\)Please read through the entire description (might need to be expanded) and the version change notes as they cover a lot of information about basic use cases and limitations. The description is always focused on the latest version. Thank you!This is an SD 1.5 LoRA for the character Dawn / Hikari from Pokemon.Example images were picked from pure 512x512 txt2img results and then re-created at 1024x1024 using txt2img with moderate Hi-res Fix settings (upscaler Lanczos, denoising strength 0.4). This improves faces and other details that are almost impossible to get correctly and consistently at 512x512 (limitation of the technology) while still giving a realistic impression of what it looks like. Pure 512x512 results will have more distorted faces and less detail.Please see the version change notes for the training and example image generation models as well as the used weights as they might change between versions. Remember that you might need to adjust weights to best suit your use case!Remember to add the tag dawn \(pokemon\) (with backslashes intact) to your positive prompt.The training set contained multiple variations of Dawn's signature look (not including alternate outfits for now, sorry) so you might need to put combinations of the following tags in your positive or negative prompts to get the desired results:beaniebraceletduffel baghairclipknee bootskneehighspoketchscarfskirtsleeveless shirtAs the training set also contained a few images with floating bits, you might need to add the negative prompts floating hair and/or floating scarf if not desired.Known Limitations / Problems:The bag and boots were not present in a lot of images and not a focus for the training so they sadly will not be consistent at all.Same goes for the bracelet and poketch but they might be a bit more recognizable from time to time.The beanie pattern needs a bit of luck to get correctly (sadly seems very difficult to train correctly).Eyes and hair had different colors (blue and black) in the training data, better to specify explicitly.You might also need to prompt for specific clothing colors from time to time, don't really know why yet.Depending on the clothing, framing etc. it may be more or less difficult to remove the beanie. I recommend a negative prompt with additional weight as well as specifying a hair color, e.g. blue hair in the positive prompts which seems to help. Still, that beanie (especially its pattern) really wants to be there.The kneehighs might sometimes result in two parts, the kneehighs themselves and a separate part at the thighs, leaving the knee exposed. No idea what causes that, it might help to put thighhighs or clothing cutout in the negative prompts.

Pokemon - Dawn / Hikari [SD 1.5 Character LoRA]

Autor: a9408020a989

Link: https://civitai.com/models/9100?modelVersionId=99550

Details

Type

LORA

Downloads

744

Uploaded

Jun 19, 2023

Base Model

SD 1.5

Trigger Words

DAWN \(POKEMON\)

Please read through the entire description (might need to be expanded) and the version change notes as they cover a lot of information about basic use cases and limitations. The description is always focused on the latest version. Thank you!

This is an SD 1.5 LoRA for the character Dawn / Hikari from Pokemon.

Example images were picked from pure 512x512 txt2img results and then re-created at 1024x1024 using txt2img with moderate Hi-res Fix settings (upscaler Lanczos, denoising strength 0.4). This improves faces and other details that are almost impossible to get correctly and consistently at 512x512 (limitation of the technology) while still giving a realistic impression of what it looks like. Pure 512x512 results will have more distorted faces and less detail.

Please see the version change notes for the training and example image generation models as well as the used weights as they might change between versions. Remember that you might need to adjust weights to best suit your use case!

Remember to add the tag dawn \(pokemon\) (with backslashes intact) to your positive prompt.

The training set contained multiple variations of Dawn's signature look (not including alternate outfits for now, sorry) so you might need to put combinations of the following tags in your positive or negative prompts to get the desired results:

beanie

bracelet

duffel bag

hairclip

knee boots

kneehighs

poketch

scarf

skirt

sleeveless shirt

As the training set also contained a few images with floating bits, you might need to add the negative prompts floating hair and/or floating scarf if not desired.

Known Limitations / Problems:

The bag and boots were not present in a lot of images and not a focus for the training so they sadly will not be consistent at all.

Same goes for the bracelet and poketch but they might be a bit more recognizable from time to time.

The beanie pattern needs a bit of luck to get correctly (sadly seems very difficult to train correctly).

Eyes and hair had different colors (blue and black) in the training data, better to specify explicitly.

You might also need to prompt for specific clothing colors from time to time, don't really know why yet.

Depending on the clothing, framing etc. it may be more or less difficult to remove the beanie. I recommend a negative prompt with additional weight as well as specifying a hair color, e.g. blue hair in the positive prompts which seems to help. Still, that beanie (especially its pattern) really wants to be there.

The kneehighs might sometimes result in two parts, the kneehighs themselves and a separate part at the thighs, leaving the knee exposed. No idea what causes that, it might help to put thighhighs or clothing cutout in the negative prompts.

Files with SHA256: 9a79e44db65536f5e1cfb3af0bcda520506678fcba7259f7eb93d53529c81159