Prompts I like with this model: (1girl, detailed eyes:1.5), black iris, beautiful eyes, masterpiece
Recommended resolution: 960x or 1024x. CFG: 6-11. I recommend not using high priority for v1 models because it will cost you many credits. Not every model is hard tested.
Note about style: You can add or remove EasyNegative and EasyNegativeV2. Try those embeddings as it changes the image. Some people may like different things.
⚠️ Here's my tutorial on how to get the best quality possible: https://youtu.be/lF5csBbVIX4
First model I did merging models. High quality anime style. Even if it is v1 the model is STILL ON BETA. Recommended: v1.2 and then other non-beta versions. Feel free to test it with new negative prompts (let me know if you think there are better ones). It works better in Stable Diffusion, as hands get better with embeddings (badhandv4 or others). v1.2 do the best hands from all the versions. Use a LoRA for hands in PixAI.
New: Everything-Mix 2D v2 now available. It is different than v1, test it and let me know how it feels: https://pixai.art/model/1690068301903299164
Some recommended tags: 1girl:1.5, dynamic pose, detailed eyes. This model seems like it doesn't need many quality tags. Don't add too many like: masterpiece, 4k, ultradetailed, high res... This model doesn't need it as much. 2-3 will make it HD, it is better to increase negative prompts for bad generation. Increase your quality tags by () if you used a least one. Also don't try high semirealistic prompts.
Recommended LoRA for hands, eyes and enhancing/more details. [NEW] Now that custom resolution is here try 960x resolution. I use that because then I can just upscale to x2.
For the best quality possible I recommend high res fix (Never use this option as default, it costs a lot) or 1024 quality. This is a high resolution model so it will be better with 1024 than 768 resolution. The more resolution, the better. For PixAI, I recommend highres fix to x1 res. because it is free. Configure it on settings with x4 batch.
Tip: What you can also do to get an amazing generation for 0 credits: Generate a image with Everything-Mix v1_EX or other model, then fix it with Everything v1.2 (as a base image) with 30 steps. Beta versions are there for enhancing, that way it show better results.
You can use any sampling method, it looks like it works with everything (20 or more steps, there are a few that can generate with less than that). My favorites for this model are Euler a, DDMI and DPM++ 2M SDE Karras. Have in mind some model versions would require more than 20 steps. Try to not show hands as it will show better results overall. Try something like "perfect hands" if you want decent hands in V1.2+.
Best samplers I tested yet in general (best to worst) with 30 steps: Euler a | DPM++ 2M SDE Karras | DDMI | DPM++ SDE | DPM++ 2M | DPM++ 2S a Karras
Also, something I noticed from my v1.2 model: Less CFG (6): More anime style. More CFG (11): More semi-realistic anime style. Use this to control semi-realism instead prompts. I recommend 6, 7, 10.5 and 11. CFG 11.5/12 can work sometimes amazingly for hands and with other negative prompts. Safer generation: CFG 7 or 11/10.5.
Comparison between versions:
v0 to v1 https://pixai.art/artwork/1664692839678748266 (v1 improved even more)
v1 to v1.1 https://pixai.art/artwork/1664870231705030661 (v1.1-Final is now v0.2-EX)
v0.5_alpha to v1.2 https://pixai.art/artwork/1665022390419102407 (v1.1 is now v1_EX)
VAE: https://pixai.art/artwork/1666542801431114911
Negative prompt: https://pixai.art/artwork/1666664414971792475
More versions from 2D v1: https://pixai.art/model/1667580698401724081
NEW! Everything-Mix 2D v2 now available: https://pixai.art/model/1690068301903299164
NEW! Everything 2D v1.1 now availlable: https://pixai.art/model/1711645636433507170
- Recap -
All versions will try to maintain the composition but will change the image, more or less.
v1_EX has a cool style but bad hands so it might need fixes with other models.
Beta V0.2-EX and EF were going to be V1.1 but they were too experimental and maybe you can get fine hands with embeddings. I like more EX than EF. Those version can create weird eyes so you need something to fix it. It looks that if you add many prompts, hands get worse.
v1.2 sometimes has some improvements in hand generation compared to v1_EX. All V1.2 versions tend to use more steps. It can be fine at 20 but it will be better with more. It looks better on a wide variety of samplers.
V0.5, V1 and V1.1 create decent N-SFW (normally has bad hands). v1.2 experimental versions doesn't create good N-SFW imo, but sometimes the result is fine. v1.2 creates good N-SFW but sometimes it requires more specific tags and steps.
This saturated VAE makes better definition images at the cost of being more saturated. Sometimes it can be helpful, but I'd prefer less saturation. My recommendation if you get more contrast and you don't like it: Use normal VAE version: https://pixai.art/model/1667580698401724081
New: Renamed v1 beta versions to 0.x instead to better clarify which one you should use.
Since I don't know much from model merging and I'm still learning, I'll keep the model private for the moment. Please don't ask for downloads. All the versions are fp16, most of them pruned.
Off-topic: If you like AI music I have an AI band. Please subscribe! https://www.youtube.com/@ForTheSkies
