Update April 28th Added version V4 pruned model.
A model with professional RPG industry artists in mind. Those working in video games, board and tabletop games as well as concept art and book covers should get good use from this model. The new version, V4, packs in more training for creatures and RPG subjects including a more illustrative style.
Detailed tutorial on how I get the results in the preview images.
Check here if you're having trouble getting the same results. Initial generation size and VAE usage is key.
You can prompt any style you need with these models, but the default aesthetic is listed for each of the models in this handy list.
Different models available, check the blue tabs above the images up top:
Stable Diffusion 1.5 (512) versions:
V4 inpaint Inpainting version of V4 that's good for outpainting.
V4+VAE Same as V4 but with the added convenience of having a preset VAE baked in so you don't need to select that each time. Saves on vram usage and possible NaN errors. Speeds up workflow if that's the VAE you're going to use anyway.
V4 New aesthetic added to make it a bit more illustrative. More training for better coherency for all things RPG.
V3+VAE Same as V3 but with the added convenience of having a preset VAE baked in so you don't need to select that each time. Saves on vram usage and possible NaN errors. Speeds up workflow if that's the VAE you're going to use anyway.
V3 Stronger painterly style. High contrast and sharpness. Even more RPG knowledge.
V3 inpaint Inpainting version of V3 that's good for outpainting.
V2 Stronger painterly style. High contrast and sharpness. More RPG knowledge.
V2 offset Noise Offset added making more contrast and bringing the model back to photoreal.
V2 Art Trained model. Very artsy. Strongest painterly style. Less details and bigger brush strokes to mimic digital painting style pre-AI.
V2 inpaint Inpainting version of V2 that's good for outpainting.
V1 Smoother renders with least painterly effect.
V1 inpaint Inpainting version of V1 that's good for outpainting.
Stable Diffusion 2.1 (768) versions:
SD 2.1 768 V1 Strong painterly style, very coherent with hands and objects. Higher native resolution and detail. Not good for nudity.
Not as effective, but here's the LoRA if you like to use that instead:
A to Zovya RPG Artist's Tools LoRA
Do you have requests? I've been putting in many more hours lately with this. That's my problem, not yours. But if you'd like to tip me, buy me a beer. Beer encourages me to ignore work and make AI models instead. Tip and make a request. I'll give it a shot if I can. Here at Ko-Fi
Description
The Stable Diffusion 2.1 768 inpainting version.
Set VAE to Automatic using 2.x models.
Good for outpainting.
Be sure to also download the config file and place in the same folder with the model.
FAQ
Comments (26)
How NSFW friendly is this model?
all the SD1.5 versions can do NSFW, the SD2.1 version will struggle a little
V2 would be the best to use. Check some of the images posted below.
I wonder how long it will take before it becomes common knowledge that SD1.5, is preferred by most, over SD2.1?
I got notified you updated the model today, but nothing seems to have changed..?
Probably it was just that a new tag was added because of the changes in the webpage. They really need to fix these notifications spam for no reason
Added the 2.1 inpainting model that was requested. Hmm, maybe I should have an updates section on the description.
@Zovya I see it now, I clicked through the various models but didn't catch the new date. Always good with updates!
@victorc25744 Yeah there is a bit of that at times.. But what would fix it in this situation, would be a visual flag for the updated model - the 2.1 Inpainting in this case, Make it glow or something, until it's been clicked on..
hey it's a very good models but what can i do so my male character don't have beards
i was making male elf and all have beards.
"no beard" ," without a beard", "shaved clean" i did not work so i add beard to negatvie prompt and i got elf woman . sorry for bad english
do you mind sharing your prompt? I'll see if I can help to fix it.
@Zovya yes sorry for responding so late
prompts"dnd character,rogue, male elf ,young,without a beard, short grey hair , 85kg, portrait, trending on artstation, mdjrny-v4 style, a highly detailed portrait painting, highelf, by greg rutkowski and alphonse mucha, sharp focus, matte, concept art, artstation, digital painting''
negative prompts "(brown eyes:1.4), (helmet), ((illustration)), ((asia)), (tattoo), face paint veil, hat, headwear, steel armor, ((medieval armor)), ((headphones)), ((headband)), tiling, 2 characters, (veil), (long hair), (braided hair), low resolution, (white clothing), ((helmet)), hat, glasses, (blue armor:1.4), ((black hair)), ((red hair:1.4)), (brunette), Dress, canvas frame, cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), weird colors, blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), Photoshop, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, 3d render"
@RUSTYRAT1234 Maybe you could try the following in combination with one another:
- Removing "without a beard" as a prompt
- Moving "beard" to negative prompt (as it sounds like you had done) and change the emphasis to see what results you can get (change the amount of brackets and weight).
- Add more emphasis to "male elf" by adding brackets
- Add "female" as a negative prompt
Not an expert on this by any means but just some thoughts on what could work.
I cannot download the configuration file(yaml) of the inpainting model. Is civitai okay?
You sure you selected the model that has the config file first?
is there a list of fantasy classes, races, creatures, and monsters this can do anywhere?
Why is the image generated by the V2 model still very gray when other parameters are the same? Is it because of the use of different VAE models?
yes. I use the VAE recommended vae-ft-mse-840000-ema-pruned. But you can get different results using other VAEs
Is normal to appear little purple spots on the image once upscaled?
no, that sounds like something is turned up too high. CFG scale, embedding, lora.
@Zovya hmm... CFG default 7, no embedding, no lora... idk... it's strange, I've just seen that this purple spots appear with first generations as well, goes bigger with the image. I've not been able to reproduce them with other models :\ I guess I need to continue testing, thanks Zovya :)
@JosephK cranking up a prompt too high could do it as well. like (masterpiece:1.8) for example. it's hard to help here. if you run into too many troubles, hop on the discord and ping me there.
@Zovya yep, I'm testing with VAE (just know about it's existence, quite new with SD)
I think it was the VAE, thank you @Zovya :D