/bbwai/ - bbwai

Stable Diffusion, Loras, Chatbots


Mode: Reply [Return] [Go to bottom]

  • Allowed file types: GIF, JPG, PNG, WebM, OGG, ZIP and more
  • Maximum number of files per post: 6
  • Maximum file size per post: 10.00 MB
Captcha no cookies?
Read the rules before you post.
Advanced (canvas, flags, deletion)
Drawing: Γ— size canvas
(For post deletion)

I trained local image generation models for generating BBW and large SSBBW images and videos. Local BBW Image & Video Models No. 41536

Open file 3.03 MB, 1536x2048

Open file 2.72 MB, 1536x2048

Open file 2.59 MB, 1536x2048
I've trained two Loras for Z-Image Turbo, and created some easy to use Workflows for ComfyUI to use these for Image and Video generation. [Feedai Lora](https://civitai.red/models/2545806/feedai) Produces realistic small to large BBW Women. Can be used with a bunch of different triggerwords including: feedai_lora_token: the basic activation trigger dOuble_b3lly_lora_token r0und_b3lly_lora_token tu88y_lora_token: on the chubbier rather than bbw side cut3_r0und_belly_lora_token B008s_lora_token: large boobs Unfortunately the model only loosely follows these triggerwords, and tends to bias towards soft double bellies. I've found leaving out any trigger words tends to be the most consistent for getting smaller, rounder bellies. [SSAIBBW Lora](https://civitai.red/models/2545842/ssaibbw) Produces unrealistically large SSBBW Women with the triggerword ssaibbw_lora_token. Each come with their own workflow (attached to the images on CivitAI), containing a wildcard prompt which will generate an infinite combination of BBWs and scenarios. The image generation workflows first produce a rought draft, and then refine this in a second polish stage. This allows for more control over the size of the BBWs without compromising realisitc detail. The strength of the Lora can be adjusted individually for the two stages, for e.g in the SSAIBBW workflow the rough draft has very poor detail, but can produce extremely large BBWs, which the model otherwise struggles with, and then can be polished to be more realistic in the second stage. The video generation workflow (attached to the videos on CivitAI) is designed to take the images and produce varried 5s videos in a batch. You select the first image in your input folder, and select the number of runs, and it will iterate through all the images. I use a NSFW lora, as this produces much more realistic jiggling. The higher the resolution, the better the detail, but this also results in much longer render times. I run these workflows on my 8GB GPU (64GB RAM), the images take ~2min, and the vidoes ~4min. I usually just queue a bunch, and let it generate overnight.
Very new to this but keen to give it a go. I have comfyui installed and running along with the lora downloaded but I am struggling to figure out the workflow? I can only find the prompts on civitai, is this the same as the workflow? any guidance much appreciated
ComfyUI embeds workflows into the images themselves. Download one of the images from CivitAI, open a new tab in ComfyUI and then drag and drop the image onto the center of the screen, that should open the workflow. You’ll then have to switch the workflow to the β€œDefault View” from the dropdown on the top left temporarily to make sure you’ve got all the right models loaded. Gemini/Claude/ChatGPT are really good with walking you through setting it up or any issues you might have, but let me know if you get stuck.
Thank you king. Been looking for a way to make bitches with elephantiasis for a while now.
>>41630 Prompt and lora you used?

Open file 2.59 MB, 2048x1536

Open file 2.64 MB, 1536x2048

Open file 2.69 MB, 1536x2048
Some more images using the Feedai lora :)

Open file 578.04 KB, 1664x928

Open file 2.27 MB, 1344x1728

Open file 2.59 MB, 1344x1728

Open file 2.31 MB, 1344x1728

Open file 2.43 MB, 1344x1728
v2 of Feedai has now been uploaded to Civitai: https://civitai.red/models/2545806/feedai
My retarded ass can't figure out how to import the workflow into comfyui. How do you?

Open file 2.30 MB, 1344x1728
You just download this image, and drag and drop it into ComfyUI, it will open the workflow. You'll need to install the missing nodes (Z-Image Turbo LoRA Loader) before running it.