We lifted 15 functions out of this paper's own repositories and ran 14 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| haoosz/vico | canonical | 14 of 15 |
| Function | Status | Where it lives |
|---|---|---|
| Normalize | Ran | haoosz/vico/ldm/modules/diffusionmodules/model.py code served (permissive licence) · get_code("9fcdaa6e423e8aa7") |
| always | Ran | haoosz/vico/ldm/modules/x_transformer.py code served (permissive licence) · get_code("fe5dd5258046898c") |
| default | Ran | haoosz/vico/ldm/modules/attention.py code served (permissive licence) · get_code("424012cb37b31172") |
| disabled_train | Ran | haoosz/vico/ldm/models/diffusion/classifier.py code served (permissive licence) · get_code("4cb732f513d69dfd") |
| exists | Ran | haoosz/vico/ldm/modules/attention.py code served (permissive licence) · get_code("aa5486a3650902d8") |
| get_bert_token_for_string | Ran | haoosz/vico/ldm/modules/embedding_manager.py code served (permissive licence) · get_code("d5726f9e3a5684c3") |
| get_clip_token_for_string | Ran | haoosz/vico/ldm/modules/embedding_manager.py code served (permissive licence) · get_code("41c6eb3a0aa3eb46") |
| get_timestep_embedding | Ran | haoosz/vico/ldm/modules/diffusionmodules/model.py code served (permissive licence) · get_code("cb49209c125de1b4") |
| isimage | Ran | haoosz/vico/ldm/util.py code served (permissive licence) · get_code("b1368330cf0f5642") |
| ismap | Ran | haoosz/vico/ldm/util.py code served (permissive licence) · get_code("d72762b700feee6f") |
| log_txt_as_img | Ran | haoosz/vico/ldm/util.py code served (permissive licence) · get_code("f41710299c49d36d") |
| nonlinearity | Ran | haoosz/vico/ldm/modules/diffusionmodules/model.py code served (permissive licence) · get_code("3137073275f8c21a") |
| uniform_on_device | Ran | haoosz/vico/ldm/models/diffusion/ddpm.py code served (permissive licence) · get_code("d48d8354986e3b0e") |
| uniq | Ran | haoosz/vico/ldm/modules/attention.py code served (permissive licence) · get_code("9a299fe5ae09e407") |
| get_embedding_for_clip_token | Not yet run | haoosz/vico/ldm/modules/embedding_manager.py code served (permissive licence) · get_code("48a80bc1b4910426") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustrated in a handful of images, into a generative model that captures fine visual details and generates photorealistic images based on textual embeddings. In this paper, we present ViCo, a novel lightweight plug-and-play method that seamlessly integrates visual condition into personalized text-to-image generation. ViCo stands out for its unique feature of not requiring any fine-tuning of the original diffusion model parameters, thereby facilitating more flexible and scalable model deployment. This key advantage distinguishes ViCo from most existing models that necessitate partial or full diffusion fine-tuning. ViCo incorporates an image attention module that conditions the diffusion process on patch-wise visual semantics, and an attention-based object mask that comes at no extra cost from the attention module. Despite only requiring light parameter training (~6% compared to the diffusion U-Net), ViCo delivers performance that is on par with, or even surpasses, all state-of-the-art models, both qualitatively and quantitatively. This underscores the efficacy of ViCo, making it a highly promising solution for personalized text-to-image generation without the need for diffusion model fine-tuning. Code: https://github.com/haoosz/ViCo
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2306.00971")
get_code_for_paper("2306.00971")
have("2306.00971")
Connect an agent — have() is free.