Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / THUDM/CogVideo issues and pull requests

#422 - Question about cfg of I2V

Issue - State: closed - Opened by luyvlei 29 days ago

#421 - Caption Upsampler codes for image-to-video

Issue - State: open - Opened by czk32611 29 days ago

#420 - Diffusers LoRA inference code does not work.

Issue - State: open - Opened by Yuancheng-Xu 30 days ago - 5 comments

#419 - demo page

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR 30 days ago

#418 - Update README.md

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 1 month ago

#417 - CogVideoX-Factory

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 1 month ago

#416 - Merge

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 1 month ago

#415 - Question help - Is it possible to clone the trasformer using copy.deepcopy ?

Issue - State: open - Opened by rodjjo about 1 month ago - 2 comments

#414 - 推理只能49帧吗

Issue - State: open - Opened by Amuseum-WHR about 1 month ago - 1 comment

#413 - Finetune stuck at vae encode

Issue - State: open - Opened by foreverpiano about 1 month ago - 2 comments

#412 - train_cogvideox_image_to_video_lora bug

Issue - State: open - Opened by luyvlei about 1 month ago - 1 comment

#411 - Add new command line arguments for LoRA weights and prompt

Pull Request - State: closed - Opened by glide-the about 1 month ago

#410 - Is there any training code?

Issue - State: open - Opened by foreverpiano about 1 month ago

#409 - index 144 is out of bounds for dimension 0 with size 144

Issue - State: closed - Opened by mercywang111 about 1 month ago - 1 comment

#408 - Multi gpu inference for image to video

Issue - State: closed - Opened by sumitmamoria about 1 month ago - 3 comments

#406 - prepare_rotary_positional_embeddings

Issue - State: open - Opened by HaoZhang990127 about 1 month ago - 1 comment

#405 - encode_video() uses pure noise as image_latent_dist？

Issue - State: closed - Opened by Verg-Avesta about 1 month ago - 4 comments

#402 - Add a pipeline that makes it possible to train 2B model with 10GB of VRAM

Pull Request - State: closed - Opened by rodjjo about 1 month ago - 3 comments

#400 - 飞书技术文档

Pull Request - State: closed - Opened by glide-the about 1 month ago

#399 - lora推理报错

Issue - State: closed - Opened by syyxsxx about 1 month ago - 1 comment

#397 - Can I reconstruct a real video with CogVideo?

Issue - State: closed - Opened by pindcog about 1 month ago - 1 comment

#396 - Why do color blocks appear in the video after changing num_frame to 25?

Issue - State: closed - Opened by pyoliu about 1 month ago - 4 comments

#395 - Does inversion work in CogVideoX?

Issue - State: closed - Opened by pindcog about 1 month ago - 1 comment

#393 - I2V diffusers SFT finetune OOM

Issue - State: closed - Opened by Verg-Avesta about 1 month ago - 7 comments

#392 - Inference latency measurement.

Issue - State: open - Opened by foreverpiano about 1 month ago

#389 - I2V Finetune of CogVIdeoX-5B-I2V

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 1 month ago

#388 - Lora training resources usage

Issue - State: open - Opened by rodjjo about 1 month ago

#386 - gradio UI for finetuning T2V AND I2V - CogVideoX 5B

Issue - State: open - Opened by GeeveGeorge about 1 month ago - 2 comments

#385 - [Q] About train dataset (amount, resolution, video length, etc...)

Issue - State: closed - Opened by KihongK about 1 month ago - 7 comments

#384 - I2V fine-tuning questions

Issue - State: open - Opened by yjhong89 about 1 month ago

#383 - fix deprecation of clear_objs_and_retain_memory

Pull Request - State: closed - Opened by LittleNyima about 1 month ago

#382 - xdit in friendly link

Pull Request - State: closed - Opened by feifeibear about 1 month ago

#381 - How to use I2V fine-tuned lora weight in the diffusers?

Issue - State: closed - Opened by asdnjadsn about 1 month ago - 3 comments

#380 - 开启deepspeed时bfloat16类型错误

Pull Request - State: open - Opened by luyvlei about 1 month ago

#379 - Update app.py

Pull Request - State: closed - Opened by AlexandrePoisson about 1 month ago

#378 - Generated video with third-party watermarks

Issue - State: open - Opened by yclin925 about 2 months ago - 1 comment

#377 - diffusers finetune error

Issue - State: open - Opened by syyxsxx about 2 months ago - 6 comments

#376 - merge

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 2 months ago

#375 - How to do batch inference?

Issue - State: closed - Opened by Florenyci about 2 months ago - 4 comments

#374 - fine-tuned I2V model generates corrupted video

Issue - State: closed - Opened by Yuancheng-Xu about 2 months ago - 9 comments

#373 - Local deployment: This problem occurs in the new version model.

Issue - State: open - Opened by ximing99 about 2 months ago - 1 comment

#371 - Multi-GPU Inference for the SAT Version

Issue - State: open - Opened by ZhengxuYan about 2 months ago

#370 - Support Multi-User for Gradio Web Demo

Issue - State: open - Opened by panpan0000 about 2 months ago - 3 comments

#369 - pad_image of rife_model.py is inaccurate can you fix it

Issue - State: open - Opened by FurkanGozukara about 2 months ago - 1 comment

#368 - Text to video and video to video doesn't work

Issue - State: closed - Opened by FurkanGozukara about 2 months ago - 4 comments

#367 - learnable_pos_embed in cogvideox_5b_i2v.yaml vs cogvideox_5b.yaml

Issue - State: open - Opened by hw-liang about 2 months ago - 1 comment

#365 - Update requirements.txt

Pull Request - State: closed - Opened by m626zNq about 2 months ago

#364 - fix the example scripts in parallel_inference_xdit.py

Pull Request - State: closed - Opened by xibosun about 2 months ago

#362 - feat: add xDiT support for parallel inference

Pull Request - State: closed - Opened by xibosun about 2 months ago

#361 - log video OOM

Issue - State: open - Opened by Eurus-Holmes about 2 months ago - 2 comments

#360 - about torch.compile

Issue - State: open - Opened by Shiroha-Key about 2 months ago - 2 comments

#359 - CogVideoX里的3d-rope是在哪里实现的呀

Issue - State: closed - Opened by HeShiLie about 2 months ago - 2 comments

#358 - bug fix rife

Pull Request - State: closed - Opened by glide-the about 2 months ago - 3 comments

#357 - video extention

Issue - State: open - Opened by HaoZhang990127 about 2 months ago - 9 comments

#356 - 2B model finetune results

Issue - State: open - Opened by mercywang111 about 2 months ago

#355 - SAT Finetuning I2V model

Issue - State: closed - Opened by Yuancheng-Xu about 2 months ago - 2 comments

#354 - Improved convenience of prompt input

Issue - State: open - Opened by Enchante503 about 2 months ago - 1 comment

#349 - Prompt conversion using Google Gemini

Issue - State: open - Opened by Enchante503 about 2 months ago - 1 comment

#348 - How to finetune CogVideoX-2B on multiple nodes?

Issue - State: open - Opened by Kyfafyd about 2 months ago

#347 - Is there a plan to release CogVideoX-2B-I2V

Issue - State: closed - Opened by JH-Xie about 2 months ago - 4 comments

#346 - Data

Issue - State: closed - Opened by Yuancheng-Xu about 2 months ago - 1 comment

#345 - Frame Interpolation is causing an error

Issue - State: open - Opened by Enchante503 about 2 months ago - 1 comment

#344 - 导出lora模型为什么报错“lora_state_dict length is not 240”

Issue - State: closed - Opened by schhaohao about 2 months ago - 1 comment

#343 - loss is NAN when training some steps, sat sft type

Issue - State: open - Opened by AlphaNext about 2 months ago - 4 comments

#342 - 请问在sat下如何进行多机训练？需要修改哪些配置呢

Issue - State: closed - Opened by QingQingS about 2 months ago - 1 comment

#340 - Do not hard code num_frames=49

Issue - State: closed - Opened by SoftologyPro about 2 months ago - 2 comments

#339 - load_cogvideox_lora.py execution error

Issue - State: open - Opened by mercywang111 about 2 months ago

#338 - [Help] Finetuning script hangs after checkpoint loading with no additional logs

Issue - State: closed - Opened by KihongK about 2 months ago - 3 comments

#337 - dynamic_cfg seems wrong in diffusers' impl

Issue - State: closed - Opened by eugenelyj about 2 months ago - 3 comments

#336 - fix: unexpected num_frames during v2v inference

Pull Request - State: closed - Opened by sculmh about 2 months ago - 1 comment

#335 - new discord

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 2 months ago

#334 - Add Replicate demo and API

Pull Request - State: closed - Opened by chenxwh about 2 months ago - 1 comment

#333 - Save prompt

Issue - State: open - Opened by Enchante503 about 2 months ago

#332 - Please do not delete the video you created.

Issue - State: closed - Opened by Enchante503 about 2 months ago - 1 comment

#331 - Request for address change

Issue - State: closed - Opened by Enchante503 about 2 months ago - 1 comment

#330 - Pylint alerts corrections as part of intervention experiment

Issue - State: open - Opened by evidencebp about 2 months ago - 1 comment

#329 - #323 Fix and CogStudio link

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 2 months ago

#328 - merge

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR about 2 months ago

#327 - How to do batch inference on CogVLM2-Caption?

Issue - State: closed - Opened by Yuancheng-Xu about 2 months ago - 3 comments

#326 - Fine-tuning results

Issue - State: open - Opened by xvjiarui about 2 months ago - 11 comments

#325 - request for inference using multiple GPUs

Issue - State: open - Opened by GeeveGeorge about 2 months ago - 7 comments

#324 - Fine tuning loss become NaN after some steps

Issue - State: open - Opened by PR-Ryan about 2 months ago - 2 comments