Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / FoundationVision/LlamaGen issues and pull requests
#60 - Only inference
Issue -
State: open - Opened by heavenhellchen 10 days ago
#59 - 请问如何用我自己的数据集训练 Image tokenizers and AR models for text-conditional image generation?请问可以提供一个示例吗,谢谢
Issue -
State: open - Opened by gzhuinjune 24 days ago
#57 - [Add]sigle gpu generation file
Pull Request -
State: closed - Opened by YecanLee about 1 month ago
#56 - About train losses and evalution parameters setting
Issue -
State: open - Opened by MrCrims about 1 month ago
#55 - About evaluation on private dataset
Issue -
State: open - Opened by MrCrims about 1 month ago
#54 - About ROPE in sample process
Issue -
State: open - Opened by Leedonus about 2 months ago
- 6 comments
#53 - Question about cannot reproduce FID results
Issue -
State: closed - Opened by Ghy0501 about 2 months ago
- 1 comment
#52 - add t5 extraction instructions in Readme or Getting started for t2i training
Issue -
State: open - Opened by sahil02235 about 2 months ago
#51 - Loss increases during training the T2I model
Issue -
State: closed - Opened by Epiphqny about 2 months ago
#50 - T2I VQVAE Training Details
Issue -
State: open - Opened by alexanderswerdlow about 2 months ago
#49 - Mask guidance, inpaiting and outpaiting
Issue -
State: open - Opened by sahil02235 about 2 months ago
- 7 comments
#48 - Cannot Reproduce LlamaGen-B or L numbers using provided models
Issue -
State: closed - Opened by vkramanuj about 2 months ago
- 1 comment
#47 - T2I performance on mscoco
Issue -
State: open - Opened by HalvesChen 2 months ago
#46 - FID results of GPT-L and GPT-1B on 256*256 images
Issue -
State: open - Opened by LutingWang 2 months ago
- 3 comments
#45 - KeyError: 'optimizer'
Issue -
State: open - Opened by sugary199 2 months ago
- 3 comments
#44 - Can LlamaGen predict a [EOS] token when inferencing?
Issue -
State: open - Opened by luminousking 2 months ago
- 6 comments
#43 - Test
Pull Request -
State: closed - Opened by Ryankwon03 2 months ago
#42 - Do you try class 2 Image generation with the image resolution of 512X512?
Issue -
State: open - Opened by OliverRensu 3 months ago
#41 - Difficulty in reproducing results with pre-trained weights
Issue -
State: open - Opened by Rishit-dagli 3 months ago
- 1 comment
#40 - tokenizer of 4 dim
Issue -
State: open - Opened by DidiD1 3 months ago
#39 - Training Results
Issue -
State: open - Opened by Huage001 3 months ago
- 4 comments
#38 - Questions about the results of your experiment.
Issue -
State: open - Opened by potatowarriors 3 months ago
- 2 comments
#37 - T2I Data
Issue -
State: closed - Opened by HalvesChen 3 months ago
#36 - 你好,vq_ds16_c2i_training.pt 在私有的通用图片上finetune效果变差了,就试了在imgenet数据集接着finetune,效果也变差了,想问一下是哪里出问题了?
Issue -
State: open - Opened by 353xiong 3 months ago
- 1 comment
#35 - Questions about the discriminator
Issue -
State: closed - Opened by Doctor-James 3 months ago
- 1 comment
#34 - FID Evaluation not matching paper results for VQ-16 checkpoint
Issue -
State: closed - Opened by vkramanuj 3 months ago
- 3 comments
#33 - Text embedding inject
Issue -
State: closed - Opened by daiyixiang666 3 months ago
- 2 comments
#32 - Inquiry about the OpenImages dataset
Issue -
State: closed - Opened by RobertLuo1 3 months ago
- 2 comments
#31 - Question about why not try using image tokenizer and a ready made llama3 etc LLM model with lora?
Issue -
State: open - Opened by lucasjinreal 3 months ago
- 9 comments
#30 - Question about text-conditional generation.
Issue -
State: closed - Opened by Yangr116 3 months ago
- 2 comments
#29 - 你好,我使用您的代码训练了我自己的数据集,但是图片变得特别模糊
Issue -
State: open - Opened by gzhuinjune 3 months ago
- 9 comments
#28 - Train script
Issue -
State: open - Opened by potatowarriors 3 months ago
- 1 comment
#27 - Discriminator is not training properly?
Issue -
State: closed - Opened by ThisisBillhe 3 months ago
- 4 comments
#26 - Which parameters are trainable? Are the encoder and decoder in VQGAN fixed? Is the llama fixed?
Issue -
State: open - Opened by tanshuai0219 3 months ago
- 1 comment
#25 - [Feature] Inpainting script
Issue -
State: open - Opened by kabachuha 3 months ago
Labels: enhancement
#24 - [Feature] ControlNet support via process similar to PixArt's ControlNet-Transformer
Issue -
State: open - Opened by kabachuha 3 months ago
- 1 comment
Labels: enhancement
#23 - [vllm] llamagen-3b
Pull Request -
State: closed - Opened by ShoufaChen 3 months ago
#22 - Mismatched model weights document
Issue -
State: closed - Opened by Artanic30 3 months ago
- 2 comments
#21 - RuntimeError: shape '[1, 512, 1, 32, 2]' is invalid for input of size 16448
Issue -
State: open - Opened by beniz 3 months ago
- 8 comments
#20 - Error in FID evaluation
Issue -
State: open - Opened by Artanic30 3 months ago
- 2 comments
#19 - Will this line of code blur the image during evaluation? tokenizer/tokenizer_image/reconstruction_vq_ddp.py: transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5], inplace=True)
Issue -
State: open - Opened by 353xiong 3 months ago
- 1 comment
#18 - why using constant lr?
Issue -
State: closed - Opened by ThisisBillhe 3 months ago
- 1 comment
#17 - Unexpected error when replicating experiments
Issue -
State: closed - Opened by ChenDRAG 3 months ago
- 3 comments
#16 - Lacks Detailed Documentation
Issue -
State: open - Opened by harsh2ai 3 months ago
#15 - VQ-VAE ckpt optimizer states?
Issue -
State: open - Opened by julian-q 3 months ago
- 5 comments
#14 - Training Details?
Issue -
State: closed - Opened by ChenDRAG 3 months ago
- 4 comments
#13 - Improve Hugging Face discoverability, make download stats work
Pull Request -
State: closed - Opened by NielsRogge 3 months ago
- 7 comments
#12 - FSDP training gets stuck after saving the weights
Issue -
State: closed - Opened by 1359347500cwc 3 months ago
- 1 comment
#11 - chore: update taming_vqgan_demo.py
Pull Request -
State: closed - Opened by eltociear 3 months ago
#10 - HF model
Issue -
State: open - Opened by edmondja 3 months ago
- 2 comments
Labels: enhancement
#9 - Could you please tell me which trick has the greatest impact on the overall effect?
Issue -
State: closed - Opened by xesdiny 3 months ago
- 5 comments
#8 - Training cost
Issue -
State: open - Opened by liming-ai 3 months ago
- 3 comments
#7 - Issues about the 3B model
Issue -
State: open - Opened by Con6924 3 months ago
- 1 comment
Labels: enhancement
#6 - About t2i weights
Issue -
State: closed - Opened by jiashenggu 3 months ago
- 1 comment
#5 - How to use with diffusers?
Issue -
State: open - Opened by s9anus98a 3 months ago
- 1 comment
Labels: enhancement
#4 - can i train in colab free?
Issue -
State: open - Opened by s9anus98a 3 months ago
- 1 comment
Labels: enhancement
#3 - ModuleNotFoundError: No module named 'vllm.engine.ray_utils'
Issue -
State: open - Opened by csdY123 3 months ago
- 1 comment
#2 - Zsl/add page
Pull Request -
State: closed - Opened by jshilong 3 months ago
#1 - update bib
Pull Request -
State: closed - Opened by jshilong 3 months ago