LokeshJonnakuti
AI & ML interests
Organizations
- Runtime errorFeatured618
LoRA Studio
πͺ618Browse and run thousands of community trained LoRAs
- Running on A100Featured1.18k
LoRA the Explorer SDXL
π1.18kExplore fun LoRAs and generate with SDXL
- Running354
Serverless ImgGen Hub
β¨354Highly hackable hub w/ Flux, SD 3.5, LoRAs, no GPUs required
- Runtime error43
Flux with Character Consistancy
πΌ43Generate images using reference images and text prompts
- Runtime error613
Kolors Portrait With Flux
π€613Kolors Portrait to keep face identity developed with Flux
- Running on ZeroFeatured1.7k
Joy Caption Alpha Two
π1.7kGenerate customized captions for any image
- Running on Zero50
CharacterFactory
πΌ50Generate consistent character images from text prompts
- Running on ZeroMCP2.76k
Background Removal
π2.76kRemove image backgrounds and get transparent PNGs
- Running on Zero304
BiRefNet Demo
π304Remove background from photos with accurate segmentation
- Runtime error6
Background Removal
π6Remove backgrounds from images using a URL or upload
- Runtime errorFeatured903
Kolors Character With Flux
π€Ή903Kolors Character to keep character developed with Flux
- Runtime error10k
Kolors Virtual Try-On
π10kTry on clothes on a person image
- Runtime error613
Kolors Portrait With Flux
π€613Kolors Portrait to keep face identity developed with Flux
-
deepseek-ai/DeepSeek-R1-0528
Text Generation β’ 685B β’ Updated β’ 899k β’ β’ 2.41k -
deepseek-ai/DeepSeek-V3-0324
Text Generation β’ 685B β’ Updated β’ 339k β’ β’ 3.09k -
deepseek-ai/DeepSeek-V3.2-Speciale
Text Generation β’ Updated β’ 15.1k β’ 688 -
deepseek-ai/DeepSeek-V3.2
Text Generation β’ 685B β’ Updated β’ 293k β’ β’ 1.33k
- Runtime errorFeatured641
FLUX.1 [Inpainting]
π¨641 - Runtime error90
FLUX.1 [Inpainting]
π¨90Generate images by repairing and modifying masked areas
- Runtime error5
FLUX.1 [Inpainting with lora]
π¨5Generate images by removing or altering masked parts using prompts and LoRA models
- Runtime errorFeatured765
Flux Fill Outpainting
π765Extend images to desired dimensions using prompts
- Configuration errorFeatured115
ViewCrafter
π¨115Create a video from an image with camera motion
- RunningFeatured88
TMR
π¨88Retrieve 3D human motion videos from text descriptions
- Runtime error10
MagicAnimate
π10Generate animated videos from images and motion sequences
- Runtime error118
MotionGPT
π118Generate human motion from text or audio
- Running on ZeroFeatured453
InstantStyle
π453Style-Preserving Text-to-Image Generation
- Running on Zero170
Flux IP Adapter
πΌ170Prompt with Images in flux[dev]
- Running on ZeroFeatured893
Flux Style Shaping
π893Optical illusions and style transfer with FLUX
- Paused56
Style Generator
π56blending randomness, creativity, and inspiration for fashion
- Running on Zero296
GenAI Arena
π296Realtime Image/Video Gen AI Arena
- Running on Zero66
Svd Keyframe Interpolation
π¨66Generate a video by interpolating between two images
- Running on ZeroFeatured325
Diffusers Image Fill
π325Fill and edit images using masks
- Running on ZeroFeatured368
LHM
β‘368Large Animatable Human Model
- Running on ZeroFeatured1.7k
Joy Caption Alpha Two
π1.7kGenerate customized captions for any image
- Runtime error1.42k
Joy Caption Pre Alpha
π¬1.42kGenerate captions for images
- Runtime errorFeatured424
Kosmos 2
π»424Describe and highlight entities in images
- Runtime errorFeatured198
Better Florence 2
π₯198Analyze images to detect objects, generate captions, or perform OCR
- Running on Zero2.61k
Voice Clone
π£2.61kClone a voice to speak any text you provide
- Runtime errorFeatured2.77k
XTTS
πΈ2.77kGenerate speech from text using a reference voice
- Running281
Voice Clone Multilingual
π281Languages ru,en,zh-cn,ja,de,fr,it,pt,pl,tr,ko,nl,cs,ar,es,hu
- Paused155
Voice Clone TTS
π155mcp_server
-
microsoft/TRELLIS-image-large
Image-to-3D β’ Updated β’ 3.59M β’ 630 - Runtime errorFeatured1.57k
InstantMesh
π1.57kCreate a 3D model from an image in 10 seconds!
- Running on A10G229
CharacterGen
π229Gradio demo of CharacterGen (SIGGRAPH 2024)
- Running on Zero112
Sketch Gen
π112Generate sketch images from uploaded photos and prompts
-
deepseek-ai/DeepSeek-R1-0528
Text Generation β’ 685B β’ Updated β’ 899k β’ β’ 2.41k -
deepseek-ai/DeepSeek-V3-0324
Text Generation β’ 685B β’ Updated β’ 339k β’ β’ 3.09k -
deepseek-ai/DeepSeek-V3.2-Speciale
Text Generation β’ Updated β’ 15.1k β’ 688 -
deepseek-ai/DeepSeek-V3.2
Text Generation β’ 685B β’ Updated β’ 293k β’ β’ 1.33k
- Runtime errorFeatured618
LoRA Studio
πͺ618Browse and run thousands of community trained LoRAs
- Running on A100Featured1.18k
LoRA the Explorer SDXL
π1.18kExplore fun LoRAs and generate with SDXL
- Running354
Serverless ImgGen Hub
β¨354Highly hackable hub w/ Flux, SD 3.5, LoRAs, no GPUs required
- Runtime errorFeatured641
FLUX.1 [Inpainting]
π¨641 - Runtime error90
FLUX.1 [Inpainting]
π¨90Generate images by repairing and modifying masked areas
- Runtime error5
FLUX.1 [Inpainting with lora]
π¨5Generate images by removing or altering masked parts using prompts and LoRA models
- Runtime errorFeatured765
Flux Fill Outpainting
π765Extend images to desired dimensions using prompts
- Configuration errorFeatured115
ViewCrafter
π¨115Create a video from an image with camera motion
- RunningFeatured88
TMR
π¨88Retrieve 3D human motion videos from text descriptions
- Runtime error10
MagicAnimate
π10Generate animated videos from images and motion sequences
- Runtime error118
MotionGPT
π118Generate human motion from text or audio
- Running on ZeroFeatured453
InstantStyle
π453Style-Preserving Text-to-Image Generation
- Running on Zero170
Flux IP Adapter
πΌ170Prompt with Images in flux[dev]
- Running on ZeroFeatured893
Flux Style Shaping
π893Optical illusions and style transfer with FLUX
- Paused56
Style Generator
π56blending randomness, creativity, and inspiration for fashion
- Running on Zero296
GenAI Arena
π296Realtime Image/Video Gen AI Arena
- Running on Zero66
Svd Keyframe Interpolation
π¨66Generate a video by interpolating between two images
- Running on ZeroFeatured325
Diffusers Image Fill
π325Fill and edit images using masks
- Running on ZeroFeatured368
LHM
β‘368Large Animatable Human Model
- Running on ZeroFeatured1.7k
Joy Caption Alpha Two
π1.7kGenerate customized captions for any image
- Runtime error1.42k
Joy Caption Pre Alpha
π¬1.42kGenerate captions for images
- Runtime errorFeatured424
Kosmos 2
π»424Describe and highlight entities in images
- Runtime errorFeatured198
Better Florence 2
π₯198Analyze images to detect objects, generate captions, or perform OCR
- Runtime error43
Flux with Character Consistancy
πΌ43Generate images using reference images and text prompts
- Runtime error613
Kolors Portrait With Flux
π€613Kolors Portrait to keep face identity developed with Flux
- Running on ZeroFeatured1.7k
Joy Caption Alpha Two
π1.7kGenerate customized captions for any image
- Running on Zero50
CharacterFactory
πΌ50Generate consistent character images from text prompts
- Running on Zero2.61k
Voice Clone
π£2.61kClone a voice to speak any text you provide
- Runtime errorFeatured2.77k
XTTS
πΈ2.77kGenerate speech from text using a reference voice
- Running281
Voice Clone Multilingual
π281Languages ru,en,zh-cn,ja,de,fr,it,pt,pl,tr,ko,nl,cs,ar,es,hu
- Paused155
Voice Clone TTS
π155mcp_server
- Running on ZeroMCP2.76k
Background Removal
π2.76kRemove image backgrounds and get transparent PNGs
- Running on Zero304
BiRefNet Demo
π304Remove background from photos with accurate segmentation
- Runtime error6
Background Removal
π6Remove backgrounds from images using a URL or upload
- Runtime errorFeatured903
Kolors Character With Flux
π€Ή903Kolors Character to keep character developed with Flux
- Runtime error10k
Kolors Virtual Try-On
π10kTry on clothes on a person image
- Runtime error613
Kolors Portrait With Flux
π€613Kolors Portrait to keep face identity developed with Flux
-
microsoft/TRELLIS-image-large
Image-to-3D β’ Updated β’ 3.59M β’ 630 - Runtime errorFeatured1.57k
InstantMesh
π1.57kCreate a 3D model from an image in 10 seconds!
- Running on A10G229
CharacterGen
π229Gradio demo of CharacterGen (SIGGRAPH 2024)
- Running on Zero112
Sketch Gen
π112Generate sketch images from uploaded photos and prompts