demos and checkpoints for Wan 2.2 models
Linoy Tsaban PRO
linoyts
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
ScenemaAI/scenema-audio liked a Space 3 days ago
victor/LongCat-Video-Avatar-1.5 updated a Space 6 days ago
the-best-team/bumblebeeOrganizations
Tools & models from the upcoming 4rd issue of AI Tools for Art π read more: https://open.substack.com/pub/multimodalaiart
CausVid is a distilled version of Wan 2.1 to run faster in just 4-8 steps, extracted as LoRA by Kijai and is compatible with 𧨠diffusers
fast & compact video generation with FramePack - a next-frame prediction neural network structure that generates videos progressively
Tools & models from the 3rd issue of AI Tools for Art π read more: https://open.substack.com/pub/multimodalaiart
Tools & models from the 2nd issue of AI Tools for Art π Read more about February's releases: https://open.substack.com/pub/multimodalaiart
Diffusion guided real image editing using semantic guidance
-
LEDITS
β458Create and edit images using DDPM and SEGA techniques
-
LEDITS++
π¦472Edit images by adding or removing concepts with text prompts
-
LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance
Paper β’ 2307.00522 β’ Published β’ 33 -
Edit Friendly Ddpm Inversion
πΌ125Edit images with text prompts using diffusion inversion
super fast few-step text-to-image & img2img diffusion models - Flux, SD3, SDXL, SD
-
FLUX.1 [Schnell]
π5.07kGenerate images from text prompts with FLUX.1-schnell
-
Hyper FLUX 8Steps LoRA
πΌ760Generate high-quality images from text prompts
-
FLUX.1 [merged]
π544Generate images from text prompts with FLUX.1
-
black-forest-labs/FLUX.1-schnell
Text-to-Image β’ Updated β’ 557k β’ β’ 4.95k
Image datasets for Dreambooth LoRA training
LTX Video 13B and 13B distilled models for video generation by Lightricks
-
LTX Video Fast
π₯1.51kultra-fast video model, LTX 0.9.8 13B distilled
-
Lightricks/LTX-Video
Image-to-Video β’ Updated β’ 452k β’ 2.19k -
Lightricks/LTX-Video-0.9.7-dev
Text-to-Video β’ Updated β’ 2.24k β’ β’ 21 -
Lightricks/LTX-Video-0.9.7-distilled
Text-to-Video β’ Updated β’ 2.53k β’ β’ 58
synthetic datasets created automatically
best & latest in music generation models
a suite of models designed to add control to the base T2I model FLUX.1, enabling the modification and re-creation of real and generated images
My favorite LoRAs - demos & checkpoints
Zero-shot pipelines for identity-preserving generation π©π»π©π»βπ€
demos and checkpoints for Wan 2.2 models
Tools & models from the upcoming 4rd issue of AI Tools for Art π read more: https://open.substack.com/pub/multimodalaiart
CausVid is a distilled version of Wan 2.1 to run faster in just 4-8 steps, extracted as LoRA by Kijai and is compatible with 𧨠diffusers
LTX Video 13B and 13B distilled models for video generation by Lightricks
-
LTX Video Fast
π₯1.51kultra-fast video model, LTX 0.9.8 13B distilled
-
Lightricks/LTX-Video
Image-to-Video β’ Updated β’ 452k β’ 2.19k -
Lightricks/LTX-Video-0.9.7-dev
Text-to-Video β’ Updated β’ 2.24k β’ β’ 21 -
Lightricks/LTX-Video-0.9.7-distilled
Text-to-Video β’ Updated β’ 2.53k β’ β’ 58
fast & compact video generation with FramePack - a next-frame prediction neural network structure that generates videos progressively
synthetic datasets created automatically
Tools & models from the 3rd issue of AI Tools for Art π read more: https://open.substack.com/pub/multimodalaiart
best & latest in music generation models
Tools & models from the 2nd issue of AI Tools for Art π Read more about February's releases: https://open.substack.com/pub/multimodalaiart
a suite of models designed to add control to the base T2I model FLUX.1, enabling the modification and re-creation of real and generated images
Diffusion guided real image editing using semantic guidance
-
LEDITS
β458Create and edit images using DDPM and SEGA techniques
-
LEDITS++
π¦472Edit images by adding or removing concepts with text prompts
-
LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance
Paper β’ 2307.00522 β’ Published β’ 33 -
Edit Friendly Ddpm Inversion
πΌ125Edit images with text prompts using diffusion inversion
My favorite LoRAs - demos & checkpoints
super fast few-step text-to-image & img2img diffusion models - Flux, SD3, SDXL, SD
-
FLUX.1 [Schnell]
π5.07kGenerate images from text prompts with FLUX.1-schnell
-
Hyper FLUX 8Steps LoRA
πΌ760Generate high-quality images from text prompts
-
FLUX.1 [merged]
π544Generate images from text prompts with FLUX.1
-
black-forest-labs/FLUX.1-schnell
Text-to-Image β’ Updated β’ 557k β’ β’ 4.95k
Zero-shot pipelines for identity-preserving generation π©π»π©π»βπ€
Image datasets for Dreambooth LoRA training