goddessOfRealism_gorV6ilxlVAE.safetensors

6.46 GB · SafeTensor · fp16 · pruned

Yêu cầu thành viên

<goddess6-ill-xl>

GoR_v6ILXL+VAE SETTINGS: DPM++ SDE Karras, DPM++ 2S a Uniform EULER A Karras clip skip 2 Steps +/-30 GFC+/-7 Well, I committed this version. Take into consideration that trying to make this model realistic may have messed with the base illustrous a bit. The effects may be surprising ;) SDE can sometimes burn through but for that Euler A is finally useful. You can also test clipskip 1, but for me it is too “smooth” PS: And one more thing, if you see that I used your original prompt, please link the post in the comment under the image. Sometimes I'm surfing the civitai gallery and testing the prompts on my models and then just can't figure out what's from where -GoR_PONY_v5ilustros_H+VAE! This is experiment, it is Pony but with a liitle of Illustrious, lets say it is beta test SETTINGS: DPM++ SDE Exponential clip skip 2 CFG: 4,5 to 6,5 Use negative prompt not only pony ones Check my pics for settings Please upload your work, it will allow me to improve the model. I myself don't have much time lately to do thorough tests -GODDESS of Realism - GoR_PONY_v4photo+VAE!b Sampling method: DPM++ SDE Karras Sampling steps: 25 up+ CFG Scale: 6.5 Width: 832 Height: 1216 Clip skip 2 For distance shot recomended ADetailer for better faces Others: I don't quite know if it makes a difference but it seems to me that it improves the quality of the images Clip skip SDXL on Emphasis mode No norm Enable T5 The models used initially before my own training to create base GoR Pony were definitely Pony Realism and probably CyberRealistic Pony, DucHaiten-Pony-Real, Zonkey - Realism, DAMN! and in v1 Everclear PNY. I don't remember all exactly because I had probably all the realistic PONY models on disk. Thank you to all the creators. GoR pony v3 The basic idea is to create the most versatile model, from nice views to NSFW and from robots and monsters to fury. V3 derives from v2art but managed to get crisp colors like in beta or 1. While the quality of textures is 100x better. I noticed that this version likes tags from sd1.5 such as HD, cinematic etc.... Also, the negative long shuttles have a very big impact but be careful. Beware of too big values especially for tags related to lighting (1.3), (1.5) and too much (((()))) etc. The model has a lot to be perfect, I'm still not satisfied with the face and hands in the distance shots. If anyone finds some lore or embedding that improves this please share in the comments. Enjoy V2art_fix+VAE! All DPM++ works good, for scifi/art 2m SDE and 2m SDE Heun for human realism best DPM++ 2S a and DPM++ 3M SDE, DPM++ SDE Karras CFG scale 8-9 Steps 30up VAE baked in clipskip 1 wuler and euler a not recomended Edit : The size of the model is a consequence of using the "checkpoint model mixer." I checked with other settings and it just comes out that way. As you can see from the added images it works correctly Edit 2: LORAs trained on Pony Diffusion and Pony Realism works good. On Everclear not. I turned on "Lora/Networks: use old method" in a1111 settings GoR_PONY_V2art: I added some custom lora to change mood of images It is very sensitive model so don't go to high with ((()))) and (1.4) All DPM++ works good, I prefer 2M karras GFC from 5 to 7 Steps 30up VAE standard sdxl clipskip 1 If you see others problems sher it so I can fix them in next version tested in automatic1111 GoR PONY_v1 GFC works up to 10 DPM++ 2M karras = fast DPM++ SDE karras = quality 3MSDE, Euler, Euler a = works fine to Steps= 30-45 VAE standard sdxl Be careful with adding too many tags like: photorealistic, photography, bokeh etc.... Sometimes their excess causes errors GoR PONY_beta DPM++ 2M SDE karras-30steps for simple image and 40-50 for more complicated, for more info check posted images dataset and compare of all samplers GFC: 2 for realistic up to 7 to get more vibrant Pony "scores" and tags for positive and negative SD:1.5 description below This is a mix of very many models from this site. The main goal was to create more artistic photographs in different styles. Prompt; photo type > angle > subject >subject details > background > quality tags (not necessarily) > style (not necessarily) samplers best with DPM++ SDE Karras steps 25+ gfc 7 hires fix as you like ( I prefer foolhardy) Clip Skip 1 It dislikes "full body shot" use full shot and others Negative prompt dangerdonkey, kkw-new-neg-v1.6 ,(low water quality:1.45), low particles efects, ( 3d render, anime, draw, cartoon, grotesque),( over saturated:1.1), jpeg artifacts, out of frame, (((watermark, signature))), lowres, (low quality skin:1.1), , error, compressed, 000, dolly skin, (plastic doll), barbie, (lolicon, loli:1.2), childlike, 000, bad anatomy, bad hands, mutated hand, missing fingers, fused fingers, extra fingers, extra arms, long neck, amputation, (poor quality feet:1.0), wrong number of feet, blending objects, extra digit, fewer digits, cropped, out of frame, error, extra limbs, mutation, bad proportions, cropped head, malformed limbs, mutated hands, mutated feet, missing limbs, cropped, deformed, ugly, mutilated, disfigured, face cut, head cut, legs cut, poorly drawn face, animals, nsfw,

SHA256

1DE51003924A1B6A46A5AFFDAE07144816A5D3B8DECD236B4167FB2D02E5E712

ID mô hình ModelTrends.ai

#8890

Sampler

DPM++ 2S a Karras

Số bước

25

Guidance

7

Kích thước

1280x1856

Sampler

Euler a

Số bước

30

Guidance

7

Seed

2092087291

Kích thước

832x1216

Clip skip

2

Sampler

Euler a

Số bước

25

Guidance

7.5

Seed

2121280594

Kích thước

832x1216

Clip skip

2

Sampler

DPM++ SDE

Số bước

30

Guidance

7

Seed

2048582429

Kích thước

832x1216

Clip skip

2

Sampler

DPM++ SDE

Số bước

25

Guidance

7.5

Seed

2887705565

Kích thước

832x1216

Clip skip

2

Sampler

Euler a

Số bước

25

Guidance

7.5

Seed

3909998537

Kích thước

832x1216

Clip skip

2

Sampler

DPM++ SDE

Số bước

25

Guidance

5

Seed

2149660808

Kích thước

832x1280