AI-generated child sex imagery has every US attorney general calling for action (arstechnica.com)
Pedos ruin everything…
SDXL 0.9 release for research, public 1.0 mid-July (stability.ai)
Apparently requirements are 8GB VRAM (16 on AMD GPUs) and 16GB system RAM.
Well, it looks like verification photos might be useless now. (startrek.website)
I loved how the details turned out (lemmy.world)
You can now request Stable Diffusion generations from the AI Horde bot directly from anywhere in lemmy! (lemmy.dbzer0.com)
cross-posted from: lemmy.dbzer0.com/post/13211160...
a16z Funded AI Platform Generated Images That “Could Be Categorized as Child Pornography,” Leaked Documents Show (www.404media.co)
While I think this is a bit overblown in sensationalism, any company that allows user generative AI, especially as open as using LoRas and any amount of checkpoints, needs to have very good protection against synthetic CSAM like this. To the best of my knowledge, only the AI Horde has taken this sufficiently seriously until now.
Shadows Don’t Lie and Lines Can’t Bend! Generative Models don’t know Projective Geometry...for now (projective-geometry.github.io)
https://projective-geometry.github.io/static/videos/Explainer_Video.mp4...
Introducing Stable Video Diffusion (youtu.be)
Abstract...
Can you hand me that gouda please? (lemmy.world)
Death (lemmy.ca)
SDXL official release date (lemmy.ca)
Link to join the discord: discord.gg/stablediffusion?event=1130919343941758…
How do you approach creating images?
Hi there, I’m curious to know other people’s approach in working with Stable Diffusion. I’m just a hobbyist myself and work on creating images to illustrate the fictional worlds I’m building for fun....
Releasing OneTrainer, a new training tool for Stable Diffusion (github.com)
OneTrainer is a tool I’ve been working on for a few months now. It can be used to fine-tune models, or train LoRAs and Textual-Inversion embeddings. More things will come in the future....
whats popin (lemmynsfw.com)
OC ControlNet did its best, despite the circumstances.
![Shaquille O'Neal hugging a little spaceship as it blasts into space, exaggerated proportions Negative prompt: thin, lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature, (deformed face), (ugly face), (eyeless), (missing nose), (mouthless), (asymmetrical face), BadNegAnatomyV1-neg, badhandv4 Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3318233218, Size: 512x768, Model hash: be1d90c4ab, Model: absolutereality_v16, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.35, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer model 2nd: hand_yolov8n.pt, ADetailer prompt 2nd: "perfect hand, masterpiece, fingers, thumb", ADetailer confidence 2nd: 0.35, ADetailer dilate/erode 2nd: 4, ADetailer mask blur 2nd: 4, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True, ADetailer inpaint padding 2nd: 32, ADetailer version: 23.7.5, ControlNet 0: "preprocessor: scribble_pidinet, model: control_v11p_sd15_scribble [d4ba51ff], weight: 0.8, starting/ending: (0, 1), resize mode: Resize and Fill, pixel perfect: False, control mode: Balanced, preprocessor params: (512, 100, 200)", Version: v1.4.0 Used embeddings: BadNegAnatomyV1-neg [05c5], badhandv4 [dba1]](https://kbin.social/media/cache/resolve/entry_thumb/ce/2c/ce2c91d367850ac2ab16e11386b354359dccc82a0035da022419e4efc50b8e6c.png)
gold and white spider man (lemmynsfw.com)
Really hard to title some of the things SD creates! (lemmy.ca)
Workflow:...
The Dinosaur with the pearl Earring (lemmynsfw.com)
Welcome all! let's start posting and get this moving... (feddit.de)
This is straight from the SDXL beta on discord... can't wait to have this to try on my own PC with Auto1111, I'm sure tweaking the step and cfg settings would fix the texture details. Already loving how much better it is at text and at composition, and from what I've read should be really easy to train and tweak.
SD QR Code Tutorial (www.youtube.com)
Stable Diffusion Prompt Book | OpenArt (openart.ai)
This is a free resource (downloadable in PDF format) with a lot of suggestions for prompting.
TheMistoAI/ComfyUI-Anyline: Anyline: A Fast, Accurate, and Detailed Line Detection Preprocessor (github.com)
DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation (i.imgur.com)
Abstract...
AI Lighting - Demonstration With Iconic Movie Scenes (www.youtube.com)
TheMistoAI/MistoLine: A Versatile and Robust SDXL-ControlNet Model for Adaptable Line Art Conditioning (github.com)
