Text-and-pose guided image generation on DeepFashion Multimodal Text2Human
23.46FIDUPGPT
Evaluation Results
| Method | Links | |
|---|---|---|
| UPGPTclothing style image embedding=without2023.04 | 23.46 | |
| Text2Human2023.04 | 24.52 | |
| HumanDiffusion2023.04 | 30.42 |
Loading the SOTA2 catalog…