chinshou

About the volume feature

6

raise NotImplementedError("the feature volume is not supported currently") It seems the framework does not support volume feature. Is there any reason that the framework can not support volume feature? I...

Volatile GPU-Util is low

6

I am testing with a GTX1070 . when running python hypersearch.py to hypersearch ,By running nvidia-smi , I found that the Volatile GPU-Util is very low (only 6%) with Perf...

I tried to preprocess_canny a bitmap with a size of 1024x1024. Due to the hardcoding of the memsize, ``` uint8_t* preprocess_canny(uint8_t* img, int width, int height, float high_threshold, float low_threshold,...

Split the api to support comfyui like workflow

1

For instance, some effects require combining multiple different control networks to achieve them, which is easy to implement in ComfyUI. However, this is not possible with the current Stable Diffusion...

report a bug instead of crash when vae_decoder_only=True and using img2img

2

At now if we use new_sd_ctx with vae_decoder_only=true , the img2img api call will crash without any exception catched. We had better checking the vae_decoder_only flag in the img2img function...

txt2img can not be called multiple times.

4

txt2img can not be called multiple times. when calling txt2img the second time it will crash at following line ` cond_stage_model->compute(n_threads, input_ids, input_ids2, max_token_idx, false, &chunk_hidden_states, work_ctx);` I suspect there...

export some api to free the image memory

1

``` for (int i = 0; i < params.video_frames; i++) { if (results[i].data == NULL) { continue; } std::string final_image_path = i > 0 ? dummy_name + "_" + std::to_string(i...