Ecosyste.ms: Issues

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

GitHub / Alpha-VLLM/Lumina-T2X issues and pull requests

#106 - Slow generation on cuda

Issue - State: open - Opened by OlegRuban-ai 3 months ago - 1 comment

#99 - When will the MV-Next-DiT model weights released?

Issue - State: open - Opened by runzeer 4 months ago

#98 - img2img script generates corrupted images

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

#98 - img2img script generates corrupted images

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

#97 - Do you have any plans to accelerate the Lumina model using TensorRT?

Issue - State: open - Opened by csdY123 4 months ago - 1 comment

#94 - Lumina-T2X VAE problem

Issue - State: open - Opened by George0726 4 months ago - 3 comments

#94 - Lumina-T2X VAE problem

Issue - State: open - Opened by George0726 4 months ago - 3 comments

#93 - lumina_next_t2i: _pickle.UnpicklingError: invalid load key, 'v'.

Issue - State: closed - Opened by Fashizel 4 months ago - 5 comments

#93 - lumina_next_t2i: _pickle.UnpicklingError: invalid load key, 'v'.

Issue - State: closed - Opened by Fashizel 4 months ago - 5 comments

#92 - Expected timeline of T2V model/code release

Issue - State: open - Opened by kkahatapitiya 5 months ago - 1 comment

#91 - Lumina Next img2img

Issue - State: closed - Opened by thelemuet 5 months ago - 7 comments

#91 - Lumina Next img2img

Issue - State: closed - Opened by thelemuet 5 months ago - 7 comments

#90 - Fine-tuning on a 24GB GPU?

Issue - State: closed - Opened by araleza 5 months ago - 1 comment

#90 - Fine-tuning on a 24GB GPU?

Issue - State: closed - Opened by araleza 5 months ago - 1 comment

#89 - cutlassF: no kernel found to launch!

Issue - State: open - Opened by zhuhw19 5 months ago - 2 comments

#89 - cutlassF: no kernel found to launch!

Issue - State: open - Opened by zhuhw19 5 months ago - 2 comments

#88 - Error when downloading LuminaModel

Issue - State: closed - Opened by ninjasaid2k 5 months ago - 1 comment

#87 - 🍊 Jupyter Notebook

Issue - State: closed - Opened by camenduru 5 months ago - 1 comment

#85 - How is captioning labeled for Lumina-T2I models?

Issue - State: closed - Opened by nunbuzor 5 months ago - 2 comments

#85 - How is captioning labeled for Lumina-T2I models?

Issue - State: closed - Opened by nunbuzor 5 months ago - 2 comments

#83 - 有计划，讲SD3的训练配置跟论文中的对齐吗

Issue - State: open - Opened by heart-du 5 months ago - 5 comments

#82 - https://huggingface.co/Alpha-VLLM/Lumina-T2Audio is 404

Issue - State: open - Opened by SoftologyPro 5 months ago - 1 comment

#82 - https://huggingface.co/Alpha-VLLM/Lumina-T2Audio is 404

Issue - State: open - Opened by SoftologyPro 5 months ago - 1 comment

#81 - ImportError: attempted relative import beyond top-level package

Issue - State: open - Opened by SoftologyPro 5 months ago - 30 comments

#81 - ImportError: attempted relative import beyond top-level package

Issue - State: open - Opened by SoftologyPro 5 months ago - 30 comments

#80 - LoRA training

Issue - State: open - Opened by KreischerPanoptic 5 months ago - 1 comment

#80 - LoRA training

Issue - State: open - Opened by KreischerPanoptic 5 months ago - 1 comment

#79 - Gated Llama-2-7b

Issue - State: closed - Opened by SoftologyPro 5 months ago - 4 comments

#79 - Gated Llama-2-7b

Issue - State: closed - Opened by SoftologyPro 5 months ago - 4 comments

#78 - Released Lumina text-to-audio code

Pull Request - State: closed - Opened by PommesPeter 5 months ago

#77 - Are Lumina-T2Audio and Lumina-T2Music the same?

Issue - State: closed - Opened by researcher48 5 months ago - 4 comments

#77 - Are Lumina-T2Audio and Lumina-T2Music the same?

Issue - State: closed - Opened by researcher48 5 months ago - 4 comments

#76 - Non-Stable Diffusion VAE for commercial usage?

Issue - State: closed - Opened by araleza 5 months ago - 4 comments

#76 - Non-Stable Diffusion VAE for commercial usage?

Issue - State: closed - Opened by araleza 5 months ago - 4 comments

#75 - Released Lumina-Audio

Pull Request - State: closed - Opened by PommesPeter 5 months ago

#75 - Released Lumina-Audio

Pull Request - State: closed - Opened by PommesPeter 5 months ago

#74 - \Lumina-Next-T2I\config.json' is not a valid JSON file.

Issue - State: open - Opened by danieldietzel 5 months ago - 3 comments

#73 - What watershed do in precompute_freq_cis function

Issue - State: open - Opened by yjhong89 5 months ago - 1 comment

#72 - Image Neural Field

Issue - State: closed - Opened by nunbuzor 5 months ago - 1 comment

#72 - Image Neural Field

Issue - State: closed - Opened by nunbuzor 5 months ago - 1 comment

#71 - fixing import errors for lumina music + lumina mini t2i

Pull Request - State: closed - Opened by npjd 5 months ago - 1 comment

#70 - What is the GPU mem requirement for finetuning?

Issue - State: closed - Opened by ninjasaid2k 5 months ago - 2 comments

#70 - What is the GPU mem requirement for finetuning?

Issue - State: closed - Opened by ninjasaid2k 5 months ago - 2 comments

#69 - Any plans integrating to diffusers?

Issue - State: closed - Opened by Luciennnnnnn 5 months ago - 3 comments

#69 - Any plans integrating to diffusers?

Issue - State: closed - Opened by Luciennnnnnn 5 months ago - 3 comments

#68 - ComfyUI support?

Issue - State: open - Opened by GamingDaveUk 5 months ago - 7 comments

#68 - ComfyUI support?

Issue - State: open - Opened by GamingDaveUk 5 months ago - 7 comments

#66 - how to try sd3 sample_sd3.py ?

Issue - State: open - Opened by s9anus98a 5 months ago - 3 comments

#66 - how to try sd3 sample_sd3.py ?

Issue - State: open - Opened by s9anus98a 5 months ago - 3 comments

#65 - Why doesn't inference time increase with pixel area?

Issue - State: closed - Opened by jiashenggu 5 months ago - 8 comments

#65 - Why doesn't inference time increase with pixel area?

Issue - State: closed - Opened by jiashenggu 5 months ago - 8 comments

#64 - Got Unpickling error when sampling lumina_next_t2i

Issue - State: closed - Opened by yjhong89 5 months ago - 2 comments

#64 - Got Unpickling error when sampling lumina_next_t2i

Issue - State: closed - Opened by yjhong89 5 months ago - 2 comments

#63 - Training details about the t2v model.

Issue - State: open - Opened by HashimotoPatrickMu 5 months ago - 1 comment

#63 - Training details about the t2v model.

Issue - State: open - Opened by HashimotoPatrickMu 5 months ago - 1 comment

#62 - Why are you using logit-normal sampling only for ImageNet experiment

Issue - State: closed - Opened by Luciennnnnnn 5 months ago - 2 comments

#62 - Why are you using logit-normal sampling only for ImageNet experiment

Issue - State: closed - Opened by Luciennnnnnn 5 months ago - 2 comments

#61 - About synthetic dataset of T2I

Issue - State: closed - Opened by jiashenggu 5 months ago

#61 - About synthetic dataset of T2I

Issue - State: closed - Opened by jiashenggu 5 months ago

#60 - Do you think using a vae with more channels is good?

Issue - State: closed - Opened by Manni1000 5 months ago - 2 comments

#59 - conrolnet support?

Issue - State: open - Opened by universewill 5 months ago - 1 comment

#59 - conrolnet support?

Issue - State: open - Opened by universewill 5 months ago - 1 comment

#58 - ComfyUI support

Issue - State: closed - Opened by doogyhatts 5 months ago - 2 comments

#58 - ComfyUI support

Issue - State: closed - Opened by doogyhatts 5 months ago - 2 comments

#57 - Question about lognorm

Issue - State: closed - Opened by jiashenggu 5 months ago - 3 comments

#57 - Question about lognorm

Issue - State: closed - Opened by jiashenggu 5 months ago - 3 comments

#56 - what is the funciton of learn_sigma

Issue - State: closed - Opened by zhangyongshun 5 months ago

#55 - I can't make it work in Colab

Issue - State: open - Opened by Quick-Eyed-Sky 5 months ago - 1 comment

#55 - I can't make it work in Colab

Issue - State: open - Opened by Quick-Eyed-Sky 5 months ago - 1 comment

#54 - Inquiry on training data and setup for T2I training

Issue - State: open - Opened by youngwanLEE 5 months ago - 2 comments

#52 - t2v timing

Issue - State: open - Opened by BurhanUlTayyab 5 months ago - 5 comments

#52 - t2v timing

Issue - State: open - Opened by BurhanUlTayyab 5 months ago - 5 comments

#51 - text to music demo not working

Issue - State: closed - Opened by Muinez 5 months ago - 3 comments

#51 - text to music demo not working

Issue - State: closed - Opened by Muinez 5 months ago - 3 comments

#50 - [feat] released `lumina-text2music` code and model

Pull Request - State: closed - Opened by PommesPeter 5 months ago

#49 - editing

Pull Request - State: open - Opened by ChrisLiu6 5 months ago

#49 - editing

Pull Request - State: open - Opened by ChrisLiu6 5 months ago

#48 - [feat] released lumina-next-compositional-generation model

Pull Request - State: closed - Opened by PommesPeter 5 months ago
Labels: enhancement

#46 - Batch Generation

Issue - State: open - Opened by HuiZhang0812 6 months ago - 3 comments

#46 - Batch Generation

Issue - State: open - Opened by HuiZhang0812 6 months ago - 3 comments

#45 - Hi , when T2A model? also T2Music? best regards

Issue - State: closed - Opened by researcher48 6 months ago - 2 comments

#45 - Hi , when T2A model? also T2Music? best regards

Issue - State: closed - Opened by researcher48 6 months ago - 2 comments

#44 - error in Next-DiT

Issue - State: open - Opened by HuiZhang0812 6 months ago - 4 comments

#43 - fix & optimization for lumina_next_t2i demo & training

Pull Request - State: closed - Opened by ChrisLiu6 6 months ago

#43 - fix & optimization for lumina_next_t2i demo & training

Pull Request - State: closed - Opened by ChrisLiu6 6 months ago

#41 - [feat] support 2k resolution inference and negative caption

Pull Request - State: closed - Opened by PommesPeter 6 months ago

#41 - [feat] support 2k resolution inference and negative caption

Pull Request - State: closed - Opened by PommesPeter 6 months ago