Even_Adder, even_adder@lemmy.dbzer0.com
Instance: lemmy.dbzer0.com
Joined: 3 years ago
Posts: 414
Comments: 63
Posts and Comments by Even_Adder, even_adder@lemmy.dbzer0.com
Comments by Even_Adder, even_adder@lemmy.dbzer0.com
They’re seemingly pissed at you too. You’re on their super-secret filtered users list.
It seems to toggle on NSFW for any post in !share_anime_art@lemmy.dbzer0.com so if I edit a post with Tesseract, I have to manually turn it off or the post will be edited to be NSFW. This is some next-level type of petty. I’ve already had to go back and fix one post it’s sabotoged.
Yeah, it’s a shame. I used this frontend too.
I’m not logged in while viewing the posts. I’m using a private tab on Firefox.
It’s back to showing nothing again for me, even with all the filters off.
This is what I saw when I tried to access !share_anime_art@lemmy.dbzer0.com. Now it shows all posts but ones from dbzer0, and it seems like every post is marked NSFW.

It doesn’t seem to be working correctly. I can’t see any posts or profiles on dbzer0.
The anime being advertised is fake, but the trailer and production are real.
It would be really cool if they didn’t do that this time.
There’s also an option to bring your own LLM, with fields for model name, endpoint, and API token available for entry when the manual option is enabled. However, the page itself warns local models may not work correctly.
It looks like there’s an option for people to self-host too. You won’t have to send your history to someone else’s computer.
I hope you do finish it. It sounds really cool.
I don’t really understand the hostility. I just asked you a question and rather than an explanation you answer with this and downvote. I guess that was my mistake for giving you the benefit of the doubt.
No one said it had to go in someone’s home. Would it not be peossible if they were able to be acquired second hand, to find use by someone or someones that weren’t the original buyer(s)?
As long as the hardware is cheap enough and gets into the right hands people will train and research to improve open models.
Cory Doctorow wrote a blog post on this.
It depends on what you mean by improve.
Calling it a “Distillation Attack” is wild. Get fucked Anthropic.
Asagao to Kase-san, a one episode OVA 00:05:25 - 00:05:57.
Yeah.










Release Raylight 1.7.2 · komikndr/raylight Added MiniMax Support, 2x Speedup (github.com)
MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video (blog.comfy.org)
astropuzzo/ComfyUI-MiniMax-H3-Image-Studio: Experimental, entirely AI-coded ComfyUI nodes for MiniMax H3 T2I, I2I, reference editing, arbitrary frames, and optimized still selection. (github.com)
docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md · MiniMaxAI/MiniMax-H3 at main (huggingface.co)
They’re seemingly pissed at you too. You’re on their super-secret filtered users list.
It seems to toggle on NSFW for any post in
!share_anime_art@lemmy.dbzer0.comso if I edit a post with Tesseract, I have to manually turn it off or the post will be edited to be NSFW. This is some next-level type of petty. I’ve already had to go back and fix one post it’s sabotoged.Yeah, it’s a shame. I used this frontend too.
I’m not logged in while viewing the posts. I’m using a private tab on Firefox.
It’s back to showing nothing again for me, even with all the filters off.
This is what I saw when I tried to access !share_anime_art@lemmy.dbzer0.com. Now it shows all posts but ones from dbzer0, and it seems like every post is marked NSFW.
It doesn’t seem to be working correctly. I can’t see any posts or profiles on dbzer0.
AsuraAce/ambit: Local-first desktop manager for AI image libraries (github.com)
ArtefactDesigntn/Jebari-ImageBatch: Custom ComfyUI nodes for batch image loading (github.com)
OpenSenseNova/SenseNova-U1: SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles V2 (github.com)
Model MD: https://github.com/OpenSenseNova/SenseNova-U1/blob/main/docs/u1_infographic_model.md
0xShug0/audio.cpp: All-in-one, inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and highly optimized performance. No Python dependency. (github.com)
Elastic Diffusion Transformer (arxiv.org)
Diffusion Transformers (DiT) have demonstrated remarkable generative capabilities but remain highly computationally expensive. Previous acceleration methods, such as pruning and distillation, typically rely on a fixed computational capacity, leading to insufficient acceleration and degraded generation quality. To address this limitation, we propose \textbf{Elastic Diffusion Transformer (E-DiT)}, an adaptive acceleration framework for DiT that effectively improves efficiency while maintaining generation quality. Specifically, we observe that the generative process of DiT exhibits substantial sparsity (i.e., some computations can be skipped with minimal impact on quality), and this sparsity varies significantly across samples. Motivated by this observation, E-DiT equips each DiT block with a lightweight router that dynamically identifies sample-dependent sparsity from the input latent. Each router adaptively determines whether the corresponding block can be skipped. If the block is not skipped, the router then predicts the optimal MLP width reduction ratio within the block. During inference, we further introduce a block-level feature caching mechanism that leverages router predictions to eliminate redundant computations in a training-free manner. Extensive experiments across 2D image (Qwen-Image and FLUX) and 3D asset (Hunyuan3D-3.0) demonstrate the effectiveness of E-DiT, achieving up to ∼2× speedup with negligible loss in generation quality. Code will be available at this https URL.
tin2tin/Asset_Generator-2D-3D: Blender asset generator for 2D and 3D (github.com)
Pallaidium: https://github.com/tin2tin/Pallaidium
Boogu/Boogu-Image-0.1-Edit-Turbo · Boogu-Image-0.1-Edit-Turbo (Image-to-Image) released (huggingface.co)
shootthesound/Fizgig: LoRA Studio — Added Support for Krea 2 With Full Feature Parity (github.com)
SurrealByDesign/comfyui-krea2-sageattention-guard: Krea 2 / Krea 2 Turbo safe SageAttention patch and workflow for ComfyUI-KJNodes (github.com)