/g/ — /sdg/ - Stable diffusion general

>mfw Resource news

06/12/2026

>ComfyUI-Flux2Klein-Enhancer: Conditioning enhancement and reference latent control
https://github.com/capitan01R/ComfyUI-Flux2Klein-Enhancer

>InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://zhengdian1.github.io/InterleaveThinker-proj

>Experimental Anima LLLite Regional Controlnet
https://huggingface.co/Sen-sou/Anima-LLLite-Regional-Controlnet

>World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible
https://haoz19.github.io/world-tracing-page

>VietFashion: Benchmarking Sketch-Text Composed Image Retrieval for Cultural Outfits
https://hng0303.github.io/VietFashion

>Modality Forcing for Scalable Spatial Generation
https://modality-forcing.github.io

>VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
https://videomdm.github.io

>EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution
https://github.com/DachunKai/EvTexture

>Budget-Constrained Step-Level Diffusion Caching
https://github.com/Westlake-AGI-Lab/BudCache

>ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
https://github.com/Snowball0823/ECA

>InterleaveThinker: Reinforcing Agentic Interleaved Generation
https://zhengdian1.github.io/InterleaveThinker-proj

>i1-3B: A Simple and Fully Open Recipe for Strong Text-to-Image Models
https://huggingface.co/zlab-princeton/i1-3B

06/11/2026

>i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
https://zlab-princeton.github.io/i1

>AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory
https://github.com/xuhang07/AnchorEdit

>Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
https://github.com/elmma/mllm-reroute

>ComfyUI-BerniniStudio
https://github.com/CCpt5/ComfyUI-BerniniStudio

>Ideoprompt: plain English to Ideogram 4 structured JSON prompt
https://github.com/cocktailpeanut/ideoprompt

>Orion4D FXMax for ComfyUI
https://github.com/orion4d/Orion4D_FXMax

>mfw Research news

06/12/2026

>TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment
https://arxiv.org/abs/2606.13035

>DuET: Dual Expert Trajectories for Diffusion Image Editing
https://arxiv.org/abs/2606.13303

>Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models
https://arxiv.org/abs/2606.12977

>ReFree: Towards Realistic Co-Speech Video Generation via Reward-Free RL and Multilevel Speech Guidance
https://arxiv.org/abs/2606.13304

>SeamEdit: A Black-Box VLM-Agnostic Pipeline for Large-Image Semantic Editing
https://arxiv.org/abs/2606.13041

>Towards More General Control of Diffusion Models Using Jeffrey Guidance
https://arxiv.org/abs/2606.13240

>AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation
https://zeyuet.github.io/AudioX-Turbo

>SmartFont: Dynamic Condition Allocation for Few-Shot Font Generation
https://arxiv.org/abs/2606.13382

>High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation
https://arxiv.org/abs/2606.12575

>Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
https://arxiv.org/abs/2606.12886

>Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration
https://arxiv.org/abs/2606.12913

>Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
https://arxiv.org/abs/2606.13558

>HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
https://arxiv.org/abs/2606.13289

>Emotional regulation improves deep learning-based image classification
https://arxiv.org/abs/2606.13081

>containment general

File: 00000200-930085360998801-z-turbo-mt.jpg (1.01 MB, 3072x2048)

>>109038457
>>109038596
zit or ig?

File: o_00092_.png (1.25 MB, 1152x896)

>>109038704
zit

File: 00000201-304053375795316-z-turbo-mt.jpg (1.02 MB, 3072x2048)

>>109038719
neat, what loras are you using (if any)?

File: Z-00344-A stylized low-poly 3D scene of a soccer stadium covered in snow with blocky benches, a huge lights, and polygonal screens, adorable quokka wearing green and red shirt with white trim, soccer ball, all rendered in a simplified geometric style.png (1.05 MB, 1152x768)

Morning anons

File: o_00093_.png (1.48 MB, 1152x896)

>>109038736
none, the prompt for that first penguin one was:
foreground: flaming axe.
midground: penguin.
background: castle.
mood: eerie, surreal.
medium: 1980s film photo.
perspective: forced, oblique.
color: very cool.
>>109038745
morning

File: 00000203-640185148455768-z-turbo-mt.jpg (1.24 MB, 3072x2048)

>>109038745
gm
>>109038753
thx

File: black_horizon-anima-2026-06-12_00220_.png (2.03 MB, 1920x1080)

>>109038745
mornin

File: download - 2026-06-12T125821.118.jpg (95 KB, 768x512)

>>109038745
I genuinely like a ton of the art you make.
Also mornin

File: o_00102_.png (1.17 MB, 1152x896)

dragon and teeth cake

File: 00042-comfyui-cfg=3.0-steps=7-ideogram4-2026-06-10-195457.jpg (406 KB, 1088x1936)

>>109037953
why?

File: 00000231-843623003079994-z-turbo-mt.jpg (925 KB, 3072x2048)

>>109040176
lel

Quite the dead shithole
Mh

File: debo_s_fia_00052_.png (2.01 MB, 1792x977)

wake up
its weekend time (argentina dub)
https://suno.com/s/NDgulWDocrYOA7US

File: debo_s_fia_00061_.png (2.31 MB, 1792x977)

>>109042950
he awakens from his slumber

File: sekhmet-anima-2026-06-13_00004_.png (2.39 MB, 1920x1080)

>>109042978
we watchin southland, its breddy good

File: sekhmet-anima-2026-06-13_00011_.png (2.13 MB, 1920x1080)

>>109043033
i like how i said this as a total non sequitur. i'm so smart

File: debo_s_fia_00059_.png (1.71 MB, 1792x977)

>>109043033
i've still never watched the wire. that'll be my cop show if i ever get an urge for a cop show

File: sekhmet-anima-2026-06-13_00019_.png (2.29 MB, 1920x1080)

>>109043099
oh yeah that one is good too. i should make a micronova song with one of these in honor of chroma