RunpeiDong / DreamLLM

[ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation

https://dreamllm.github.io/

RunpeiDong/DreamLLM Issues

Pre-trained weights for SDXL version
Updated 4 days ago
transformers version error
Updated 6 days ago1
Could yo release the code for preparing MMC4-core dataset to get correct tarfiles?
Updated 10 days ago
How can I simultaneously generate interleaved image and text content?
Updated 6 days ago2
How to train with laion400m data in Stage1?
Updated 6 days ago1
How can I input multiple images?
Updated 6 days ago1
Question regarding the details of training DreamLLM
Closed 6 days ago7
How to construct MultimodalContent for negative prompt?
Closed 6 days ago1
What did the <dream> token learn exactly?
Closed a month ago5
How to generate interleaved content creation examples shown in Fig 3 of the paper
Updated a month ago1
Will dreamllm's checkpoint be released
Closed 2 months ago1
vm_loss config
Closed a month ago3
How does shard_list.json looks like.
Closed 2 months ago1
Question about the generation of conditional embeddings
Closed 2 months ago1
Clarification Regarding Visual embeddings
Closed 7 months ago2
where to try?
Closed 2 months ago1
Looking forward to the code
Closed 2 months ago5