hotshotco/Hotshot-XL
✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL
PythonApache-2.0
Issues
- 0
- 1
- 1
Garbage GIF output
#55 opened by GARV-k - 1
- 0
How to use finetuned SDXL without LORA
#54 opened by khayamgondal - 2
Training Data
#17 opened by ruoshiliu - 0
How to load sd-xl 512 weights and finetune?
#52 opened by ersanliqiao - 0
Enhanceai.art - I recently attempted to create my own text-to-GIF enhancement feature to enhanceai.art. However, upon discovering that the source code for a similar functionality is available on GitHub, I realized that my efforts were rendered useless. In light of this, I would like to request the availability of the open source code for the text-to-GIF enhancement feature.
#51 opened by itspranavajay - 0
Training data
#50 opened by guoqincode - 0
Training SDXL based LORA
#49 opened by BlakeOne - 1
Finetune, cuda out of memory
#47 opened by xiefan233 - 0
GPU shows out of memory
#46 opened by tom9225 - 1
Question for finetune
#45 opened by xiefan233 - 0
RuntimeError: Input type (float) and bias type (c10::BFloat16) should be the same
#44 opened by xiefan233 - 0
Pip errors
#43 opened by pavankay - 1
On Custom Finetuning : RuntimeError: Input type (float) and bias type (c10::BFloat16) should be the same #bug
#36 opened by sanjay7178 - 2
SDXL-512 model still reports errors
#38 opened by lckj2009 - 1
lora not work
#37 opened by 823863429 - 1
Where is the paper?
#40 opened by howardgriffin - 0
- 0
- 0
How many GPU you used?
#39 opened by syguan96 - 1
EinopsError:
#32 opened by XTRMsavage - 2
Poor results on own pretrained SDXL
#30 opened by julkaztwittera - 5
ValueError: unet/hotshot_xl.py as defined in `model_index.json` does not exist in hotshotco/Hotshot-XL
#29 opened by billzhao9 - 1
About the training dataset
#34 opened by Kevin-1342 - 1
How do we cite the model?
#33 opened by jinga-lala - 0
ValueError: Module down_blocks.0.resnets.0.time_emb_proj is not a LoRACompatibleConv or LoRACompatibleLinear module.
#31 opened by zhou-linpeng - 0
- 1
ERROR: Could not find a version that satisfies the requirement nvidia-cudnn-cu11==8.5.0.96 (from versions: 0.0.1.dev5, 8.9.4.19, 8.9.4.25, 8.9.5.29, 2021.10.26, 2021.11.18, 2021.12.8, 2022.1.13, 2022.4.2, 2022.5.19) ERROR: No matching distribution found for nvidia-cudnn-cu11==8.5.0.96
#24 opened by My12123 - 0
These instructions don't work as written.
#25 opened by RamboRogers - 1
Training Dataset of Hotshot-XL
#23 opened by yzhang2016 - 2
Minimum required VRAM?
#2 opened by blueangel1313 - 1
[Question] What are recommended parameters for transforming existing 1920x1080 footage?
#22 opened by vedantroy - 1
How to use SDXL finetunes and LoRAs
#21 opened by godimarcovr - 2
Merge with diffusers
#20 opened by sepal - 3
--spatial_unet_base How to use?
#18 opened by wangyong860401 - 1
DownBlock3D does not exist.
#15 opened by songyiren98 - 1
Difference between AnimateDiff and Hotshot
#13 opened by MaxLeung99 - 4
Json for Diffusers download
#10 opened by tin2tin - 0
Using --video_length= and/or --video_duration= always yields "Warrning - setting num_images_per_prompt = 1.......
#9 opened by CCpt5 - 1
Fine-tuning time estimation
#3 opened by bonlime - 4