stable_diffusion
@stable_diffusion@lemmy.dbzer0.com
This is a remote community, information on this page may be incomplete. View at Source ↗
Discuss matters related to our favourite AI Art generation technology
Also see
- Stable Diffusion Art (See its sidebar for more GenAI Art comms)
- !aihorde@lemmy.dbzer0.com
Other communities
- !auai@programming.dev
- !ArtificialIntelligence@kbin.social
- Qwen-Image-2.1 in ComfyUI: Open-Weight Image Generation and Editing, Now with Transparencyblog.comfy.org ↗Submitted 2 days ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- SparknightLLC/ComfyUI-NodeSnapshots: Individual node snapshots and bounded link caching for a 2-3x frontend FPS increase and smoother ComfyUI workflow navigation.github.com ↗Submitted 2 days ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Submitted 2 days ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- SupraLabs/Supra2-IMG · a tiny 100M parameters text-to-image (T2I) model that has been trained from scratch on high-quality synthetic data and delivers state-of-the-art image quality for its size.huggingface.co ↗Submitted 2 days ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- The AI Horde has a new Interface, a new Image generation frontend, new backend, and all new documentation!haidra.net ↗Submitted 5 days ago by db0@lemmy.dbzer0.com | 0 comments
- Adudeguyman/ComfyUI-Fantastic-MiniMaxH3-PromptBuilder: A prompt builder and media manager for MiniMax H3github.com ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- lvladikov/Krea2-Turbo-Distill-2step-LoRA · A quarter of the steps · 4.2× faster denoising · fine detail at 1.01–1.17× the teacher's across all 12 trained resolutionshuggingface.co ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- supElement/ComfyUI_MinimaxH3_AutoContext: A long video generation solution that breaks through the memory barriergithub.com ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Robert1212star/TaoMate-H3-3Step-ComfyUI · ComfyUI-compatible conversion of the official TaoMate-H3 3-Step LoRA for MiniMax H3huggingface.co ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- lvladikov/Krea2-Turbo-Distill-2step-LoRA · A LoRA for Krea 2 Turbo that takes the model from its usual 8 steps down to 2huggingface.co ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Uncertainty DMD | SIGGRAPH Asia 2026 · Restoring Diversity in Few-Step Autoregressive Video Distillationscdzx.github.io ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- circlestone-labs/MiniMax-H3-Image-Training-Adapter · An adapter that allows training MiniMax H3 LoRAs on images, while preserving the distillation and quality of the base modelhuggingface.co ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Speach1sdef178/ComfyUI-VDN-H3-24GB: 24GB-optimized VDN-H3 hybrid attention implementation for MiniMax H3 in ComfyUIgithub.com ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Lightricks/LTX-2.5-22b-IC-LoRA-Ingredients · An IC-LoRA trained on top of LTX-2.5-22B, which conditions video generation on a reference sheethuggingface.co ↗Submitted 1 week ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- F16/krea2-turbo-sda · A rank-32 LoRA for Krea 2 Turbo that restores the sampling diversity the Turbo distillation removed, without degrading image quality or prompt adherencehuggingface.co ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- WASasquatch/was-node-suite-comfyui: WAS-NS Reborn; Tools for image processing, filters, masking, text, logic, numbers, latents, files, 3D scenes, and animationgithub.com ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- sepiablue-ai/ComfyUI-MiniMax-H3-W4A4-VSA: MiniMax H3 Ref2VA acceleration with FC1 ConvRot W4A4 and Streaming VSA for ComfyUIgithub.com ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- multimodal-art-projection/YuE: YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.github.com ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Submitted 2 weeks ago by businesshow@lemmy.world | 0 comments
- lvladikov/Krea2-Turbo-Distill-4step-LoRA · Half the steps · ~1.6× faster · 45% of the gap to the 8-step teacher closed · texture at 1.03× the teacher'shuggingface.co ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- speach1sdef178/MiniMax-H3-Semantic-Bridge · Cross-Architecture Semantic Transfer and Distillation for Video Generationhuggingface.co ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Kablex/ComfyUI-Ref2VA-VSA: Breakthrough inference speed for MiniMax H3 Reference-to-Videogithub.com ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- jalrobustvfx/ComfyUI-Tab-Sticky-Extention: ComfyUI Tab Sticky Notes puts an editable note under each workflow tab.github.com ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- WarmBloodAban/Minimax-h3_Singularity · A comprehensive fine-tuned fusion model specialized in enhancing the capabilities of MiniMax-H3huggingface.co ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- nvidia/Qwen3.8-Flash-Next-NVFP4 · A quantized version of Alibaba's Qwen3.8-Flash-Next modelhuggingface.co ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
- rzgar/minimax-h3_fl2v_8Step_motion_enhancer · An 8-step LoRA for the MiniMax-H3 FL2VS video model, built on top of the vanilla LightX2V 8-step LoRAhuggingface.co ↗Submitted 2 weeks ago by Even_Adder@lemmy.dbzer0.com | 0 comments
