This is photographic SDXL model derived from Pony, Ebara.

I'm releasing this model version 0.1 as feasibility study and proof of concept. I will be able to make version 1.0 if somehow I'll be able to find more time and money.

If you would like me to pursue farther on Pony-based photographic SDXL model, donation with a message can be made here: https://ko-fi.com/eeb_p I can use it to build a better model. Please bare in mind, there is no promise. I might run away with the money.

(More descriptions about proof of work will be written later.)

Tips

Positive Prompt

score_9, score_8_up, score_7_up, best quality, masterpiece, [source_anime:photo:0.01], real, eye_focus, ultrarealistic, photorealistic, natural skin, detailed skin,

Weaker Photo-Style Positive Prompt

score_9, score_8_up, score_7_up, best quality, masterpiece, [source_anime:photo:0.01], real, [:eye_focus, ultrarealistic, photorealistic, natural skin, detailed skin:0.5],

Negative Prompt

score_5, score_4, worst quality, low quality, normal quality, messy drawing, amateur drawing, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, source_furry, source_pony, source_cartoon, abstract, art_nouveau, oekaki, toony, comic, source filmmaker, 3d, blurry, cropped, text, error, signature, watermark, username, artist name,

Versions

Version 0.1: This is proof of concept.

Source

This model derived from

Pony Diffusion V6 XL

https://civitai.com/models/257749/pony-diffusion-v6-xl

Ebara

Training

Multiple photograph files of multiple peple (all age over 20 at time of photos taken) were trained for PonyDiffusion model to make LoRA.

One training was to achieve structural features of photograph.

One training was to achieve stylistic features of photograph.

Result LoRAs from both training was merged to ebora model.

Result

Trained model successfully output photographic image.

Faces of output photograph seems to defuse all trained faces, and does not seem to　resemble any particular one person in the training set.

Problem and Next Step

Teeth are crooked. I can try to get photos of people with better aligned teeth.

Faces are mostly same. I can try to merge more pony-derived base-model with more variation in faces.

Mouth is big. Eyes are big. I can try to get photos of people with mouth, and try to merge more pony-derived base-model with smaller mouth.

Some prompt gives you strong anime-style that cannot this model cannot turn it to photographic image. For those cases, you're on your own to come up with better prompt.

Licenses

Refer to the license of other models in the source.

Also refer to licensing terms and conditions on this page

For commercial use, refer to my profile.