What up coomers <3 It's been awhile since I've posted anything over in the Hunyuan thread. I felt like I'd hit a wall with progress for Lora improvement. Luckily, Wan2.1 (t2v + i2v) was released...and wow. It blows Hunyuan out of the water in pretty much every application. Not only that, but the diffusion-pipe was updated to support training almost immediately and the datasets for Hunyuan/Wan are interchangeable. I trained my first Lora last night - ga1n3rb0t_wan2.1 version 1.0. I've been testing it out today and I am more than pleased with the results. I'm not exaggerating when I say, 99% of generations are keepers. Wan2.1 has exceptional understanding when it comes to prompt adherence and appears to train much easier than Hunyuan. My current Lora is trained for the Wan2.1 14B T2V model which can generate 480p or 720p videos. I have no idea if it would work for the I2V or 1.3B models, it's possible, but I haven't tested it out. JSYK: For local generation, like Hunyuan, Wan2.1 is very resource heavy and generation times can take a few minutes. However, new workflows are quickly being released to accommodate lower-end consumer cards. I've seen some for 6GB of VRAM already. Keep your eyes on CivitAI, I'm sure you could find something that'll work for your setup. Like with Hunyuan, to experience this tech to it's full potential, I recommend renting a runpod. As always, I plan on releasing this Lora publicly ASAP. Unfortunately, CivitAI has not yet updated their models to include Wan2.1, so I am just waiting on that. As soon as it becomes available, I will upload it there and create a post here with a link to the page. Until then, I am happy to take prompt requests which I will generate and post here. Finally, here are some examples of what I have generated so far. I'm excited to hear what you think. I'll continue posting throughout the day as generations come in. Thanks for the support. -drewski

so tiktok/capcut has a new ai effect/filter which can make a video of person in a picture inflate like a balloon and is currently popular this thread is dedicated to sharing videos that use this effect currently this ai effect is for capcut pro members only you can find more videos using this effect with the links to the sounds associated with them: https://www.tiktok.com/music/original-sound-7475326177885424406 https://www.tiktok.com/music/BALLOON-FILTER-7475388181154253590 https://www.tiktok.com/music/original-sound-7475319398821677846

I've found a prompt to create to umamusume morphs! You could do this with other characters but I haven't tried with anything other than umas. Prompt: "Make the anime woman as fat as the cartoon character. Exactly the same size, proportions, anatomy, etc as the cartoon character. Maintain the face and art style of the anime woman in the end result." Compatible artist: Idle-minded Skelesoda Huwom_XL Batspid2 Bamboo ale (theory) These are the artworks that work best with the original images of the umas (obtained from the fandom wiki) and the prompt. Artwork from artists like "darkfireballz" does not work well since the AI can not comprehend what the hell is going on in the image. Notes: if you get the "nooo muh guidlines :(" just start another conversation and retry. If the end result looks like crap, try 2 or 3 more tries and more often than not it should work.

Can I post some fat male AI in this board?

weirdobeardo89 recently pulled all his games from the net with no way of getting them. I'm asking if anyone has copies of his games to please share them. they were quest games using AI images. I don't have anything to offer as the games were pulled.

Post fat anime girls with a Christmas theme

ZImage Turbo used with Qwen_3_4b for CLIP. Qwen_3_4b is a language model that understands things, so this combo can do complex prompts (20k tokens?) and compose images..with okay-ish adherence (check the 1st two images) but of course it'll run for much longer then. The only drawback is that if you describe any features of an object or person which aren't supposed to be seen from the viewing angle you specify, the model WILL change the angle to make them seen. I think if you want to use a specific character with ease, you have to make a lora - because editing detailed prompts to exclude details that momentarily cannot be seen is a pain. It runs okay on a 4070, or even 3060, with decent generating times. (1280x1024 in ~30 secs). If you want previews in okay resolution, can go down to 12 seconds or even less if low. The fp8 model is just 6gb. Not censored but has shit data on nsfw items so doesn't draw them well. Loras for that are out. It does render fatties out of the box decently up to a respectable size but struggles with ssbbw sizes as it doesn't really know how to do belly aprons and fat folds and so on. Stretchmarks etc no dice either, but seems to do okay on cellulite etc. There's few loras for it yet... just released last week.

i've been using AI to fantasize about this lady i know. it started from a photo and ive done some wild shit, what do y'all think about it? PD: she is a real yoga teacher

Does anyone have the extended version to this or other videos from the expansion archives that are not on the YouTube channel?

So there's been a lot of chatbot threads, and they're helpful, but having dipped my toes into NAI after seeing all the struggles with the current chatgpt stuff, I'm curious if anyone has found any particularly good things that help with writing there. I'm talking specific things you want to put in memory, or the lorebook, that might help it do anything from weight gain to inflation to berries, whatever it is someone wants to do. It seems like there's a lot less information on that end, despite how open it is for nsfw content.

Why not?

My new obsesion

Hey Guys. Wanted to open this thread so we could discuss about Character.ai's new feature; Scenes. We could share our scenes since it's kinda hard to search for them. Or request scenarios to creators, or even discuss new ideas to make new scenarios. Enjoy!

Hi guys I used Midjourney a couple of years ago. Version 4 was fine — each new version made the images more expressive and with fewer visual flaws (like messed-up fingers), but at the same time, they started matching the prompts less and less. Early on, it might’ve drawn imperfect or unrealistic stuff, but at least it was exactly what I asked for. Later, that gradually changed — unfortunately, for the worse. The v6 seemed to completely ignore the words like “fat”, “obese”, “wide hips” etc. Share your experience here

Post your ideal ai generated lolis who are much wider than they’re tall whether it be ones you’ve created or ones you admire. Generations depicting children are not allowed: make sure your posted gens are fictional characters that look distinctly different from actual human children Previous Thread: >>23765