2D 3D-Daz 3D-Blender Fan Art AI True Bond Art Assets, Fan Art, And Skills Discussion

[Night Hacker]

Two years ago we were talking about 3060's and the like. Now how do you feel about RTX 4070 TI Super? I'm thinking of upgrading~

View attachment 3750009​

I've written out complete scenarios, now I'm thinking about dedicating a GPU to help visualise the story.

Wow! 16G?! That price seems very nice as well. So long as there's no heating issues with it (I've heard things about the 4000 series and heating issues, but I admittedly know little about that), I would go for it. Faster and 16G of VRAM is sweet.

 

[Night Hacker]

Wow! 16G?! That price seems very nice as well. So long as there's no heating issues with it (I've heard things about the 4000 series and heating issues, but I admittedly know little about that), I would go for it. Faster and 16G of VRAM is sweet.

Hmmm... all the 4070's I see now are 12G models. Still not too bad, but I paid under $400CDN for my 3060 12G.

Edit: okay, it's the 4070TI Super that is 16G, and around $1100 CDN. I'll pass.

 

[david123]

You must be registered to see the links

Hey P4124v4n thanks for the Lora!
Was able to create this using nova_cross



Face looks a bit scary but I think thats because of the styling Lora i used.

 

[BigIrishLug]

Hey P4124v4n thanks for the Lora!
Was able to create this using nova_cross

View attachment 3770782 View attachment 3770785

Face looks a bit scary but I think thats because of the styling Lora i used.

Honestly, I don't know who this is supposed to be. Not trying to be mean, but I think your original Lora trainer was closer to the mark.

 

[P4124v4n]

Hey P4124v4n thanks for the Lora!
Was able to create this using nova_cross

View attachment 3770782 View attachment 3770785

Face looks a bit scary but I think thats because of the styling Lora i used.

You need to play around with the prompt to make her look more like in the game, try this prompt template:

Positive prompt:
((jessica-cloudlet, cleavage, covered nipples, areola slip, brown nipples, dark hair, dark eyes, detailed lips)), ((perfect fingers)), (shiny skin:0.5), (pubic hair), (milf), score_9, score_8_up, score_7_up, score_6_up,, BREAK,
INSERT ANYTHING ELSE HERE

Negative prompt:
score 1, score 2, score 3, source_western, source_comic, source_anime, source_furry, ((holding phone)), ((teeth)), worst quality, low quality, text, censored, deformed, bad hand, ugly, deformed, noisy, blurry, distorted, grainy, ((face mask)), ((beard)), ((adult male)), ((old male)), ((crossed eyes)), ((male six pack)), ((muscular male)), disfigured, poorly drawn hands, mutation, mutated, extra limb, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, extra fingers, mutated hands, deformed, mutilated, mangled

I am using fooocus so the usage of the trigger word can differ if you are using something else

 

[BigIrishLug]

This thread is for identifying assets and constructive comments in regards to fan art, ideas regarding the True Bond game in any format. As the thread creator, that is the rule, as stated on the very first page. Please read the first page again.

 

[spikor]

You need to play around with the prompt to make her look more like in the game, try this prompt template:

Positive prompt:
((jessica-cloudlet, cleavage, covered nipples, areola slip, brown nipples, dark hair, dark eyes, detailed lips)), ((perfect fingers)), (shiny skin:0.5), (pubic hair), (milf), score_9, score_8_up, score_7_up, score_6_up,, BREAK,
INSERT ANYTHING ELSE HERE

Negative prompt:
score 1, score 2, score 3, source_western, source_comic, source_anime, source_furry, ((holding phone)), ((teeth)), worst quality, low quality, text, censored, deformed, bad hand, ugly, deformed, noisy, blurry, distorted, grainy, ((face mask)), ((beard)), ((adult male)), ((old male)), ((crossed eyes)), ((male six pack)), ((muscular male)), disfigured, poorly drawn hands, mutation, mutated, extra limb, missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, extra fingers, mutated hands, deformed, mutilated, mangled

I am using fooocus so the usage of the trigger word can differ if you are using something else

Thanks for the additional info, was trying the lora but with no png or example prompt it was kinda difficult to get good results. What model do you suggest to use the lora with?

 

[P4124v4n]

Thanks for the additional info, was trying the lora but with no png or example prompt it was kinda difficult to get good results. What model do you suggest to use the lora with?

This particular lora is trained on pony models and it only works with them, you can find them on civitai, I usually use autimism mix dpo. I also have a lora trained that works with most sdxl models but they don't generate nsfw that well.

 

[spikor]

This particular lora is trained on pony models and it only works with them, you can find them on civitai, I usually use autimism mix dpo. I also have a lora trained that works with most sdxl models but they don't generate nsfw that well.

I took it for granted it was a pony model Maybe I messed up somewhere, but I tried with 3DPonyVision which is the best 3D pony model I've found so far, and the results were... bad.
What weight do you use for the trigger word? Also, can you maybe share some png with metadata so i can have a look at cfg, steps, prompts, sampler etc.

 

[P4124v4n]

I took it for granted it was a pony model Maybe I messed up somewhere, but I tried with 3DPonyVision which is the best 3D pony model I've found so far, and the results were... bad.
What weight do you use for the trigger word? Also, can you maybe share some png with metadata so i can have a look at cfg, steps, prompts, sampler etc.

Hmm, did you try with the the prompt and the exact model I pasted above? Here is my fooocus output html file using 3DPonyVision, maybe that will help. It's not the best model tbh.

 

[spikor]

Hmm, did you try with the the prompt and the exact model I pasted above? Here is my fooocus output html file using 3DPonyVision, maybe that will help. It's not the best model tbh.

thanks for the images and logs, very helpful!
I've tried with the prompts in the log, both with 3dPonyVision and Autism Mix. Yet she still is somewhat different than the original? There is a resemblance there somewhere, i get much better results now... I feel like at 1.0 lora weight she comes out too "boney", but if i lower the weight it starts changing the face.

Just out of curiosity, how did you train the lora? Did you take each img from the game and caption it?

 

[P4124v4n]

thanks for the images and logs, very helpful!
I've tried with the prompts in the log, both with 3dPonyVision and Autism Mix. Yet she still is somewhat different than the original? There is a resemblance there somewhere, i get much better results now... I feel like at 1.0 lora weight she comes out too "boney", but if i lower the weight it starts changing the face.

Just out of curiosity, how did you train the lora? Did you take each img from the game and caption it?

She looks different because you are prompting for a realistic face but her face is from a game (3d render, unity asset, etc), so the model has to add some details to the face it knows and that changes it.

Took me a long time and around 7 versions to get a good image dataset, if you want to create your own image datasets for loras this is my work flow;

- Get all images from some game of the character you want to use
- Get images of the character without anyone else in the frame
- Crop the images as close to the character as you can
- Create variations of each image by cropping closely to specific body parts that you want the model to focus on (ex. face, breasts, ass, face + upper body, face + upper body + thighs, full body)
- I don't use captions because I noticed that the model does it better on its own

This is her face without making her look realistic


{
"prompt": "((jessica-cloudlet, eyebrows, dark eyes, detailed closed seductive smile, skin pores)), Close-up details, realistic style photo, outstanding style, tall, Use soft lighting to cast gentle shadows on the subject, adding a touch of dimension to your images without compromising details, score_9, score_8_up, score_7_up",
"negative_prompt": "(score_6, score_5, score_4), ((teeth)), camera, monochrome, asymmetrical face, asymmetrical eyes, (Child, Children, Teen:1.4), (pony girl, my little pony, horse, pony,animal,furry) censored, (monochrome, disformed, 3 legs, 6 toes, (6 fingers), low-res, bad anatomy, ((bad hands)), text, error, too many fingers, ((missing hand)), missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), (disconnected limbs, mutation, mutated, amputation)",
"prompt_expansion": "",
"styles": "[]",
"performance": "Quality",
"resolution": "(1152, 896)",
"guidance_scale": 4,
"sharpness": 2,
"adm_guidance": "(1.5, 0.8, 0.3)",
"base_model": "duchaitenPonyXLNo_ponyNoScoreV40.safetensors",
"refiner_model": "None",
"refiner_switch": 0.5,
"clip_skip": 2,
"sampler": "dpmpp_2m_sde_gpu",
"scheduler": "karras",
"vae": "Default (model)",
"seed": "135399334303687349",
"lora_combined_1": "jessica-cloudlet-pony.safetensors : 1.0",
"metadata_scheme": false,
"version": "Fooocus v2.4.3"
}