Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / lucidrains/imagen-pytorch issues and pull requests
#380 - Questions about Text-to-Image training
Issue -
State: closed - Opened by xiaoxiaodadada 7 months ago
- 2 comments
#379 - how to run this code, please provide the step for text to image , please
Issue -
State: open - Opened by rajnish159 9 months ago
- 2 comments
#378 - import Imagen returns BeartypeDecorHintParamDefaultViolation
Issue -
State: closed - Opened by benjaminorr 10 months ago
- 2 comments
#377 - Any specific reason sampling is not in FP16?
Issue -
State: open - Opened by danbochman 11 months ago
- 2 comments
#376 - NameError: name "model_validator" is not defined with version 1.26.1
Issue -
State: closed - Opened by niklasbubeck about 1 year ago
- 1 comment
#375 - Backward problem with using DDP
Issue -
State: open - Opened by clearlyzero about 1 year ago
- 1 comment
#374 - pydantic fixes and cli sample fix
Pull Request -
State: closed - Opened by TheFusion21 about 1 year ago
- 2 comments
#373 - improvement
Pull Request -
State: closed - Opened by TheFusion21 about 1 year ago
- 8 comments
#372 - Subprocess Error during Wheel Build: Missing File
Issue -
State: open - Opened by KillshotELOx about 1 year ago
#370 - GPU memory increases with the number of GPUs used
Issue -
State: open - Opened by DuanXiaoyue-LittleMoon about 1 year ago
#369 - Why concatenate lowres before last conv?
Issue -
State: open - Opened by ifeherva about 1 year ago
#367 - Super-resolution not completely respecting input low resolution image
Issue -
State: open - Opened by AhmedGamal411 over 1 year ago
#366 - Triton Python 3.10 and up
Issue -
State: closed - Opened by Jammers33 over 1 year ago
- 1 comment
#365 - Can anyone look over my script and see if I've made any errors?
Issue -
State: open - Opened by Shikamaru5 over 1 year ago
#364 - text prompts
Issue -
State: closed - Opened by Shikamaru5 over 1 year ago
#363 - Bug Fix: Accelerator scaler set after Accelerator.__init__()
Pull Request -
State: closed - Opened by gauenk over 1 year ago
- 4 comments
#362 - Question about reproducing training images using respective training texts
Issue -
State: open - Opened by AhmedGamal411 over 1 year ago
#361 - how ta activate shuffle for DataLoader?
Issue -
State: open - Opened by TheZaind over 1 year ago
#360 - Question about ConnectionError
Issue -
State: open - Opened by aoyang-hd over 1 year ago
#358 - Question about retraining/fine-tuning EncoderModel with new words in `t5.get_tokenizer()`
Issue -
State: open - Opened by Kevin7720 over 1 year ago
- 2 comments
#357 - Assert prevents mixed_precision?
Issue -
State: closed - Opened by mattmisk over 1 year ago
- 3 comments
#355 - OutOfMemoryError
Issue -
State: open - Opened by nwoyecid over 1 year ago
- 3 comments
#354 - Correct Way to train both unets
Issue -
State: open - Opened by gauravbyte over 1 year ago
- 1 comment
#353 - App para contratar servicios de eventos
Issue -
State: open - Opened by Vaalaadeez over 1 year ago
#352 - how to train your inpainting model using my own dataset??
Issue -
State: open - Opened by dreamlychina over 1 year ago
- 1 comment
#351 - fix typo in self_cond
Pull Request -
State: closed - Opened by animebing over 1 year ago
- 1 comment
#350 - trainer.train_ Incorrect use of step in text to video
Issue -
State: open - Opened by yangyudong2020 over 1 year ago
#349 - Visualization of the network
Issue -
State: open - Opened by kirilllzaitsev over 1 year ago
#348 - GPU memory usage VS GPU utilization
Issue -
State: open - Opened by kirilllzaitsev over 1 year ago
- 3 comments
#347 - Samples after training only contain white noise.
Issue -
State: open - Opened by Valerie9696 over 1 year ago
- 7 comments
#346 - How many images I need to generate an fine model
Issue -
State: open - Opened by liulwx over 1 year ago
- 1 comment
#344 - Can anyone reproduce the results of the paper?
Issue -
State: closed - Opened by dreamlychina over 1 year ago
- 1 comment
#343 - Question about Classifier-free Guidance
Issue -
State: open - Opened by lucala almost 2 years ago
- 1 comment
#342 - No such file or directory
Issue -
State: closed - Opened by lijain almost 2 years ago
#341 - train
Issue -
State: open - Opened by lijain almost 2 years ago
- 1 comment
#339 - Distributed Training Gets Stuck?
Issue -
State: open - Opened by pjspol almost 2 years ago
- 1 comment
#338 - Inpainting with Videos (UNET3D)
Issue -
State: closed - Opened by MrBirrd almost 2 years ago
- 2 comments
#337 - Generated samples contain only noise while training unconditional Imagen
Issue -
State: open - Opened by lucala almost 2 years ago
- 2 comments
#336 - Working with images and text embeddings of different shape
Issue -
State: open - Opened by AhmedGamal411 almost 2 years ago
#335 - multiple values for unet_number
Issue -
State: closed - Opened by Shikamaru5 almost 2 years ago
- 1 comment
#334 - Num_Samples
Issue -
State: closed - Opened by Shikamaru5 almost 2 years ago
#333 - Seek for advice to reproduce Gen-1
Issue -
State: open - Opened by liuquande almost 2 years ago
- 1 comment
#332 - Text to video no Attentions layers
Issue -
State: open - Opened by axel588 almost 2 years ago
- 2 comments
#331 - Load materialized data from disk
Pull Request -
State: closed - Opened by jamesr66a almost 2 years ago
#330 - Little issue, No module named 'lion_pytorch'
Issue -
State: closed - Opened by axel588 almost 2 years ago
- 1 comment
#329 - ElucidatedImagen no text conditionning
Issue -
State: closed - Opened by axel588 almost 2 years ago
- 2 comments
#328 - Why not using CLIP ?
Issue -
State: closed - Opened by axel588 almost 2 years ago
- 3 comments
#327 - Pretrained Model
Issue -
State: open - Opened by wyfzka almost 2 years ago
- 8 comments
#325 - text_embeds in trainer.sample() does not work properly
Issue -
State: open - Opened by bekhzod-olimov almost 2 years ago
- 1 comment
#324 - Loss flattens out after 50k training steps
Issue -
State: open - Opened by alif-munim almost 2 years ago
- 1 comment
#323 - Decoder specified not to be conditioned on text, yet it is presented
Issue -
State: open - Opened by bekhzod-olimov almost 2 years ago
#322 - Feature/attention visualization
Pull Request -
State: closed - Opened by MischaD almost 2 years ago
#321 - Temp
Pull Request -
State: closed - Opened by HReynaud almost 2 years ago
#320 - Partial ignore time causes increased memory usage
Issue -
State: open - Opened by HReynaud almost 2 years ago
- 2 comments
#319 - Hurricane
Pull Request -
State: closed - Opened by jamesthesnake almost 2 years ago
#318 - does image_embed_dim do anything?
Issue -
State: closed - Opened by jaded0 almost 2 years ago
- 1 comment
#317 - Veryyy slow on 16x16, Text to Image, Training
Issue -
State: open - Opened by axel578 almost 2 years ago
#316 - Same Image whatever the input text on conditionnal train
Issue -
State: open - Opened by axel588 almost 2 years ago
- 1 comment
#315 - Noise on all image for training
Issue -
State: open - Opened by axel588 almost 2 years ago
- 3 comments
#314 - Model distillation
Issue -
State: open - Opened by HReynaud almost 2 years ago
- 13 comments
#313 - Bug if temporal_downsample_factor has more than 2 values
Issue -
State: closed - Opened by HReynaud almost 2 years ago
- 1 comment
#312 - Noisy / blank samples after many training steps
Issue -
State: closed - Opened by alif-munim almost 2 years ago
- 2 comments
#311 - forward() does not support the video frames arguments
Issue -
State: closed - Opened by youbin2014 almost 2 years ago
- 5 comments
#310 - multi-gpus with max_batch_size > 1 with ddp
Issue -
State: open - Opened by xqun3 almost 2 years ago
- 2 comments
#309 - trainer.save on distributed case
Issue -
State: open - Opened by TLB-MISS almost 2 years ago
- 3 comments
#308 - DDP in multi-gpu
Issue -
State: closed - Opened by webdxq almost 2 years ago
- 7 comments
#307 - Improvements for beginners
Issue -
State: open - Opened by TheFusion21 almost 2 years ago
- 6 comments
Labels: help wanted, good first issue
#306 - Support for Re-Imagen
Issue -
State: open - Opened by monatis almost 2 years ago
- 9 comments
#305 - Video temporal upsampling
Issue -
State: closed - Opened by HReynaud almost 2 years ago
- 32 comments
#304 - Unconditional Imagen
Issue -
State: closed - Opened by bekhzod-olimov about 2 years ago
- 3 comments
#303 - Is there any public weight for this opensource imagen implementation that I can have a try?
Issue -
State: closed - Opened by eeyrw about 2 years ago
- 1 comment
#302 - Running causes frozen(unresponsive device)
Issue -
State: open - Opened by troy600 about 2 years ago
- 1 comment
#301 - Ignoring time while training video diffusion is does not work when using dataloader.
Issue -
State: closed - Opened by jaded0 about 2 years ago
- 5 comments
#300 - Absurd memory usage (>512GB?!) when trying to train 256x256->1024x1024 network
Issue -
State: closed - Opened by jameshball about 2 years ago
- 9 comments
#297 - CLI error
Issue -
State: open - Opened by emma3826 about 2 years ago
- 5 comments
#296 - accelerate config, and proper Imagen scripts
Issue -
State: closed - Opened by Shikamaru5 about 2 years ago
#295 - The setup
Issue -
State: closed - Opened by Shikamaru5 about 2 years ago
- 2 comments
#294 - Training the Unets
Issue -
State: closed - Opened by Shikamaru5 about 2 years ago
- 2 comments
#293 - Poor inpainting performance when `inpaint_resample_times>1`
Issue -
State: open - Opened by jameshball about 2 years ago
#292 - Inpainting doesn't work due to error with `inpaint_masks` shape
Issue -
State: closed - Opened by jameshball about 2 years ago
- 2 comments
#291 - 2-fold, tensor conflicts, and loss:nan
Issue -
State: closed - Opened by Shikamaru5 about 2 years ago
- 1 comment
#290 - Jump length for inpainting
Issue -
State: open - Opened by jameshball about 2 years ago
- 1 comment
#289 - saving the checkpoint
Issue -
State: closed - Opened by Shikamaru5 about 2 years ago
- 1 comment
#288 - Collator crashes if sequences of different length
Issue -
State: closed - Opened by cyrilzakka about 2 years ago
#287 - Hi, any pretrained model?
Issue -
State: closed - Opened by fido20160817 about 2 years ago
#286 - Suggested hparams for video diffusion
Issue -
State: open - Opened by ezhang7423 about 2 years ago
#285 - CLI Command Infinite Download Issue
Issue -
State: closed - Opened by AngryChihuahua04 about 2 years ago
- 2 comments
#284 - CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)`
Issue -
State: closed - Opened by cyrilzakka about 2 years ago
- 1 comment
#282 - Fix feature dimensions in default configuration.
Pull Request -
State: closed - Opened by windsorwho about 2 years ago
- 1 comment
#281 - questions in the paper
Issue -
State: closed - Opened by fido20160817 about 2 years ago
- 2 comments
#280 - Regarding classifier-free guidance
Issue -
State: open - Opened by xiankgx about 2 years ago
- 1 comment
#279 - No module named 'imagen_pytorch.t5'; 'imagen_pytorch' is not a package
Issue -
State: closed - Opened by 2kinto about 2 years ago
- 2 comments
#278 - Where can I download the ready-made model?
Issue -
State: closed - Opened by xiaocdh about 2 years ago
- 1 comment
#277 - More Unets
Issue -
State: open - Opened by sr5434 about 2 years ago
- 5 comments
#276 - Is this repo of imagen generate better results than the dalle2 repo?
Issue -
State: open - Opened by universewill about 2 years ago
- 1 comment
#275 - text2video - Comparing Notes
Issue -
State: open - Opened by gowdygamble about 2 years ago
- 9 comments
#274 - Fixes
Pull Request -
State: closed - Opened by TheFusion21 about 2 years ago
- 1 comment
#273 - broken 1.16
Issue -
State: closed - Opened by TheFusion21 about 2 years ago
- 3 comments
#272 - unet.self_cond error
Issue -
State: closed - Opened by Darius-H about 2 years ago
- 1 comment
#271 - combine trainer accelerate.prepare calls to accommodate deepspeed
Pull Request -
State: closed - Opened by gowdygamble about 2 years ago
- 2 comments