* add request_id in params and filename (#285)
* animatediff_output.py filname add request_id
* Update animatediff_ui.py AnimateDiffProcess add request_id param
* allow request_id empty ,and remove from webui
* move request_id at last in init method
* remove request_id from webui
---------
Co-authored-by: zhangruicheng <zhangruicheng@migu.cn>
* fix device
* request id
* add test
* fix test
* fix test
* fix test
* cheaper test
* cheaper test
* readme
* run one test at one time
* readme
* use ubuntu 20.04
---------
Co-authored-by: zhangrc <zrc_java@163.com>
Co-authored-by: zhangruicheng <zhangruicheng@migu.cn>
* better naming convention
* add date
* api return b64 video
* hook encode_pil_to_base64
* use date instead of datetime
* remove unnecessary code for ipadapter
* vram optim
* recover from assertion error such as OOM without the need to re-start
* bugfix
* add todo to pr a1111
* fix lllite, fix absolute path, fix infotext
* fix api
* readme
* partially finish hotshotxl, have to deal with another bug
* unknown bug
* remove print
* fix mm
* remove beta, prev
* basic use supported. CN and prompt travel still on the way
* uncomment all control models for sdxl
* prompt travel
* readme
* readme
* prepare for next pr
* use state dict key to guess mm version
* replace match case with if else
* Feature png output folder (#170)
* make a subfolder for PNG outputs
* revert changing outpath_samples
* move dot to extension strings
* save png to folder
* make option animatediff_do_not_save_samples
* edit
* edit
---------
Co-authored-by: zappityzap <you@example.com>
Co-authored-by: Chengsong Zhang <continuerevolution@gmail.com>
* Added easy to understand tooltips for missing tooltips (#151)
* Added easy to understand tooltips for missing tooltips
Used an AI to make easy tooltips.
* move tooltip to js, but leave some content to a future pull
---------
Co-authored-by: Chengsong Zhang <continuerevolution@gmail.com>
* install imageio[ffmpeg] automatically
* readme
---------
Co-authored-by: zappityzap <128872140+zappityzap@users.noreply.github.com>
Co-authored-by: zappityzap <you@example.com>
Co-authored-by: Jack Smith <jackdsmith2327@gmail.com>
* readme
* alright, I just added the core code, but I don't want to test now
* probably supported?
* method in cli implemented successfully
* update frames same as fps (#185)
Co-authored-by: zappityzap <you@example.com>
* return all interpolated frames for api calls (#177)
* readme
---------
Co-authored-by: zappityzap <128872140+zappityzap@users.noreply.github.com>
Co-authored-by: zappityzap <you@example.com>
* start to support prompt travel
* these changes might be aborted
* maybe batch cond uncond has been supported
* forgot to modify one
* readme
* remove unused import
* remove another import
* ui, some readme and specification
* readme
* cfg finish
* cfg in main script
* cn on the way
* first attempt to support motion lora
* motion lora should be ready
* made some progress, but still need to hack cn main
* alright, at least import problems have been resolved. Let's do hijack for CN
* logger
* should have done cn, not tested
* format
* at least we can hack cn now
* cn finally working
* still cannot support inf v2v
* readme
* Safetensors loading (#132)
* safetensors loading
* fix erroneous change
* fix model loading
adding all safetensor models to zoo
* import sd_models.read_state_dict
---------
Co-authored-by: Rickard Edén <rickardeden@gmail.com>
Chengsong Zhang
Dan S