ContextDiff icon indicating copy to clipboard operation
ContextDiff copied to clipboard

[ICLR 2024] Contextualized Diffusion Models for Text-Guided Image and Video Generation

Results 6 ContextDiff issues
Sort by recently updated
recently updated
newest added

在ContextDiff_finetune.py文件中虽然传入了context_shift为True ![QQ图片20240524005015](https://github.com/YangLing0818/ContextDiff/assets/157948426/092a5211-9042-4da7-8c6a-d148e175535f) 但在video_diffusion.pipelines.ddim_spatial_temporal.DDIMSpatioTemporalStableDiffusionPipeline的prepare_latents_ddim_inverted函数中却将context_shift注释了,这是什么意思,有使用到context_shift吗 ![QQ图片20240524005328](https://github.com/YangLing0818/ContextDiff/assets/157948426/8a9f9f56-8c25-4d7c-ab61-e3345ecaf3ab) 以及ddim_clean2noisy_loop函数也将context_shift注释了 ![QQ截图20240524005903](https://github.com/YangLing0818/ContextDiff/assets/157948426/4643dac8-2cf7-446a-a60d-dad6b89416a8)

raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/ckpt/stable-diffusion-v1-4/resolve/main/tokenizer/tokenizer_config.json The above exception was the direct cause of the following exception:

how can I test your model and get inference??

Hello, I have reviewed the content you wrote in the ‘readme’ for text guided image generation. In the parameters of the second step 'Finetune Diffusion Model with Context-Aware Adapter', it...

why is the value of \k_t set as in the paper? ![image](https://github.com/user-attachments/assets/b21bce46-3070-41ce-bffc-37cbdc2176eb)

Hello, could you please clarify which specific network framework is used for the Relational Network mentioned in the paper? Additionally, could you point out in which class and function the...