PixArt-alpha/PixArt-sigma
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
PythonAGPL-3.0
Issues
- 0
Adapt to SD-v3's VAE
#114 opened by k-zha14 - 0
requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/PixArt-alpha/PixArt-XL-2-512x512/resolve/main/config.json
#113 opened by YMKiii - 0
PixArt license with commercial projects?
#112 opened by araleza - 0
ControlNet training code
#111 opened by cseander - 0
Train a full checkpoint - not LoRa
#110 opened by Samael-1976 - 5
PixArt Sigma output image is only messy noise
#109 opened by VGF64 - 11
Inference is quite slow on A10
#92 opened by souvikqb - 3
VRAM memory requirements for lora / finetuning?
#89 opened by GavChap - 1
How much VRAM required for Share Captioner?
#103 opened by Han230104 - 5
There is a gap with stable diffusion
#53 opened by conansherry - 0
Question About kvcompress
#108 opened by berryxue - 7
Question about VAE adaption stage
#50 opened by piddnad - 4
- 0
If I want to add a new person in the generate model, how many data should I prepare for finetuning ?
#107 opened by ApolloRay - 0
- 0
DMD for own model
#105 opened by hzhupku - 9
256x256 PixArt-Sigma model, only get a FID-30k nearly ~49 on coco2014 val , is that normal?
#46 opened by Gus-Guo - 3
[bug report] multi-aspect ratio training
#85 opened by linnanwang - 1
How can PixArt-sigma generate higher resolution images beyond training-resolution?
#99 opened by llstela - 4
how to train sigma lora?
#90 opened by YLongJin - 0
LoRA training from local models
#100 opened by GavChap - 0
how to give a lora scale in inference
#98 opened by xiaowen0110 - 2
Inpainting
#86 opened by berryxue - 4
add_noise training details
#91 opened by kelisiya - 2
Diffusers model loading Issues
#76 opened by nbardy - 1
Is lora only for alpha?
#68 opened by berryxue - 3
Img2Img pipeline for pixart
#73 opened by frutiemax92 - 1
How to img2img?
#69 opened by berryxue - 1
Train DMD !
#93 opened by ApolloRay - 3
- 1
- 5
What are the extra 4 channels from the denoiser?
#81 opened by samedii - 1
- 2
where can I find config.json?
#79 opened by 1sheep1 - 2
Question about Samplers
#65 opened by YanzuoLu - 1
Max_length in lora training
#67 opened by berryxue - 1
interface.py中168行拼写bug:imrage_size
#71 opened by liangwq - 1
train dataset
#78 opened by dangweili - 14
- 3
Fine-tuning script based on diffusers
#72 opened by youngwanLEE - 1
VAE for the DMD model
#56 opened by EternalEvan - 4
- 5
How to use the DMD checkpoint?
#49 opened by EternalEvan - 1
train speed seems too slow
#54 opened by Hazarch - 7
- 5
Cannot load a Lora safetensors file
#47 opened by ukaprch - 3
参考图
#52 opened by linghu-cell - 1
高分辨率的图就是直接 resize 放大的?
#48 opened by wodsoe - 2
- 2