Shadowgraph
About
Sign in

yresearch/Switti

Model

21

stars

6

commits

5

repos using this model

1

linked in READMEs

Dec 3, 2024

updated

safetensors
text-to-image

README

Model

drawing

Switti - Scale-wise transformer for text-to-image synthesis is a scale-wise transformer for text-to-image generation.

Model Description

  • Developed by: Yandex Research
  • Model type: Scale-wise text-to-image generative model

Evaluation

drawing

The bar chart above shows user preference for Switti vs competitor models with respect to different aspects.

Contributors

dbaranchuk

3 commits

AntonVoronov

2 commits

SpiridonSunRotator

1 commits

Similar repos

yandex-research/switti

(CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

205

MeissonFlow/Meissonic

Model

107

shihaozhao/LaVi-Bridge

Model

12

Efficient-Large-Model/Sana_1600M_512px_MultiLing

Model

16

black-forest-labs/FLUX.1-schnell

Model

5,784

nvidia/Cosmos-Predict2-0.6B-Text2Image

Model

14

Alpha-VLLM/Lumina-mGPT-2.0

Model

84

Collov-Labs/Monetico

Model

66

Used in code

viettmab/CGCE

Official PyTorch implementation of "CGCE : Classifier-Guided Concept Erasure in Generative Models"

5

1 file

AmirMaEl/VAR-Depth

4

1 file

AmirMaEl/MLN

Official codebase for 'Prompt-Guided Image Editing with Masked Logit Nudging in Visual…

3

1 file

jonasricker/prada

[CVPR Findings 2026] PRADA: Probability-Ratio-Based Attribution and Detection of…

2

1 file

seruva19/kubin-extensions

Extensions for Kubin.

2

1 file

Linked in READMEs

yandex-research/switti

(CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

205

README badge

yresearch/Switti

Model

21

stars

6

commits

5

repos using this model

1

linked in READMEs

Dec 3, 2024

updated

safetensors
text-to-image

README

Model

drawing

Switti - Scale-wise transformer for text-to-image synthesis is a scale-wise transformer for text-to-image generation.

Model Description

  • Developed by: Yandex Research
  • Model type: Scale-wise text-to-image generative model

Evaluation

drawing

The bar chart above shows user preference for Switti vs competitor models with respect to different aspects.

Similar repos

yandex-research/switti

(CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

205

MeissonFlow/Meissonic

Model

107

shihaozhao/LaVi-Bridge

Model

12

Efficient-Large-Model/Sana_1600M_512px_MultiLing

Model

16

black-forest-labs/FLUX.1-schnell

Model

5,784

nvidia/Cosmos-Predict2-0.6B-Text2Image

Model

14

Alpha-VLLM/Lumina-mGPT-2.0

Model

84

Collov-Labs/Monetico

Model

66

Used in code

viettmab/CGCE

Official PyTorch implementation of "CGCE : Classifier-Guided Concept Erasure in Generative Models"

5

1 file

AmirMaEl/VAR-Depth

4

1 file

AmirMaEl/MLN

Official codebase for 'Prompt-Guided Image Editing with Masked Logit Nudging in Visual…

3

1 file

jonasricker/prada

[CVPR Findings 2026] PRADA: Probability-Ratio-Based Attribution and Detection of…

2

1 file

seruva19/kubin-extensions

Extensions for Kubin.

2

1 file

Linked in READMEs

yandex-research/switti

(CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

205

README badge

Contributors

dbaranchuk

3 commits

AntonVoronov

2 commits

SpiridonSunRotator

1 commits