sayzardFeb 28

TechRadar (@techradar)

Nano Banana 2의 이미지 프롬프트 예시들이 공개되어 해당 버전의 성능 향상과 개선된 이미지 생성 능력을 보여줍니다. (이미지 프롬프트를 통해 새 모델의 강화된 세부 표현력 및 출력 품질을 시연하는 내용)

https://x.com/techradar/status/2027557618408149013

#nanobanana2 #imagegeneration #generativeai #diffusionmodels

TechRadar (@techradar) on X

Nano Banana 2 image prompts that showcase its powerful enhancements https://t.co/PAcKNiiD5O

X (formerly Twitter)
Bogdan BuduroiuFeb 24

Steerling-8B, the first interpretable model that can trace any token it generates to its input context, concepts a human can understand, and its training data.

https://www.guidelabs.ai/post/steerling-8b-base-model-release/

#AI #InterpretableAI #DiffusionModel #DiffusionModels

Steerling-8B: The First Inherently Interpretable Language Model

We release Steerling-8B, an 8B-parameter causal diffusion language model that is interpretable by construction — its predictions are routed through concepts you can measure, audit, and control.

Guide Labs
PsychoticSheepFeb 17
🎉 Now videos are alive! After finally getting WAN 2.1 running on my RX 6700 XT via ROCm and ComfyUI, even complex prompts can be turned into animated WebPs locally!

These animated WebP were generated locally using ComfyUI and the WAN 2.1 T2V 1.3B (fp16) model.

Model Stack:
- wan2.1_t2v_1.3B_fp16
- umt5_xxl_fp8_e4m3fn_scaled (Text Encoder)
- wan_2.1_vae
- clip_vision_h

The prompt is first converted into embeddings by the UMT5 encoder.
The WAN video model then generates multiple frames using latent diffusion (noise → iterative refinement), ensuring temporal coherence between frames.
The VAE decodes the latent frames into images, exported as an animated WebP.

Prompt execution time: depends on scene complexity, from 521.62 seconds (~8.7 minutes) up to 17 minutes 26 seconds for more complex prompts.

Rendered locally via ROCm on my AMD RX 6700 XT (12GB VRAM).
No cloud. Pure local inference.

#ComfyUI #WAN21 #ROCm #AMD #LocalAI #FOSS #VideoAI #AIvideo #AIGenerated #MachineLearning #DeepLearning #DiffusionModels #TextToVideo #AIArt #CreativeAI #LocalInference #VideoGeneration
sayzardFeb 11

fly51fly (@fly51fly)

논문 'Blind denoising diffusion models and the blessings of dimensionality' (Z. Kadkhodaie, A. Pooladian, S. Chewi, E. Simoncelli, Simons Foundation & Yale University, 2026)이 arXiv에 게시되었음을 알리는 트윗입니다. 블라인드 디노이징 확산모델과 고차원성의 이점에 관한 연구 결과를 소개합니다.

https://x.com/fly51fly/status/2021704465548726357

#diffusionmodels #denoising #arxiv #research

fly51fly (@fly51fly) on X

[LG] Blind denoising diffusion models and the blessings of dimensionality Z Kadkhodaie, A Pooladian, S Chewi, E Simoncelli [Simons Foundation & Yale University] (2026) https://t.co/sOEbQeqrcZ

X (formerly Twitter)
Wayne RadinskyJan 30

AI Motion Control takes a video and a photo and it transfers the motion of the person in the video to the person in the photo.

The demos where they transfer video to a cartoon character are cute. When they do it to a real person, it feels a bit creepy because it looks real. At least that's my take.

https://aimotioncontrol.net/

#solidstatelife #ai #genai #computervision #diffusionmodels

AI Motion Control - Precise Control Of Character Actions And Expressions

AI Motion Control platform for transferring movements and expressions from videos to images. Create lifelike video animations with precision.

AI Motion Control
PsychoticSheepJan 26
The first upload went a bit sideways -.-

Some data got lost causing black stripes in the original masterpiece image so I moved it back in the carousel

Here is the real clean version finally posting the image as it was meant to be seen

#sdxl #stablediffusion #comfyui #aiart #animeart #generativeart #diffusionmodels #foss #opensource #digitalart #animegirl
PsychoticSheepJan 26
Generated with SDXL in ComfyUI

First three images are the final results,
image #4 shows the full ComfyUI workflow used to create them.

#sdxl #stablediffusion #comfyui #aiart #animeart #generativeart #diffusionmodels #foss #opensource #digitalart #animegirl
sayzardJan 25

fly51fly (@fly51fly)

새 논문 'Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model'가 공개되었습니다. 저자 C. Fan, W. Heng, B. Li, S. Liu 등은 코드 확산(code diffusion) 기반의 대형 언어 모델을 제안하며, Huazhong University of Science and Technology와 ByteDance Seed 소속 연구진으로 2026년 arXiv에 게재되었습니다(링크 포함).

https://x.com/fly51fly/status/2015540411155251456

#codegeneration #diffusionmodels #llm #research

fly51fly (@fly51fly) on X

[CL] Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model C Fan, W Heng, B Li, S Liu... [Huazhong University of Science and Technology & ByteDance Seed] (2026) https://t.co/2FlI1BX6hR

X (formerly Twitter)
sayzardJan 23

Torsten Brezesinski (@TBrezesinski)

Materials Futures에 'DiffNMR: diffusion models for nuclear magnetic resonance spectra elucidation'라는 논문이 게재되었다고 알리는 공지입니다. Gen Long, Xin Chen, Mingjun Xiao 등(USTC, Baidu 참여)이 diffusion models를 핵자기공명(NMR) 스펙트럼 해석에 적용한 연구로, IOP 출판을 통해 오픈액세스로 공개되었습니다.

https://x.com/TBrezesinski/status/2014349539826712950

#diffusionmodels #nmr #materialsfutures #research

Torsten Brezesinski (@TBrezesinski) on X

New Paper out in #MaterialsFutures | "DiffNMR: diffusion models for nuclear magnetic resonance spectra elucidation" (Gen Long, Xin Chen, Mingjun Xiao & coworkers @ustc #SZL @Baidu_Inc) ➡️ https://t.co/O9YVGcjR0v. @IOPPublishing @IOPmaterials #OpenAccess

X (formerly Twitter)
PsychoticSheepJan 21
If you can run FLUX and SDXL locally, you really don’t need cloud AI services anymore.
No subscriptions, no prompt logging, no rate limits, just full control.

And no, you don’t need an RTX 5090 or a Radeon AI PRO R9700 (I’d love to have one though xD).
Every image here was rendered on an AMD RX 6700 XT, a mid-range GPU from 2021, not even officially supported by ROCm.

Local models. Local compute. Local freedom.

#SDXL #StableDiffusion #LocalAI #GenerativeArt #OpenSource #FOSS #PrivacyFirst #NoCloud #AMD #RX6700XT #ROCm #Linux #AIArt #DiffusionModels #CreativeCoding #MidrangeGPU #SelfHosted #Decentralized