YangLing0818/RPG-DiffusionMaster
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)
Jupyter NotebookAGPL-3.0
Issues
- 1
Can you provide more details on how you enhanced stability for extracting regional prompts?
#55 opened by andupotorac - 0
generation object outside of the region
#54 opened by X-fxx - 0
Batch Generation Support
#53 opened by itsazibfarooq - 0
- 1
Error occurs for parsing gpt4's response
#50 opened by Genie-Kim - 1
Diffusion acceleration support
#51 opened by andupotorac - 4
Enhancing Entity Recognition in Complex Scenes for Text-to-Image Diffusion Models
#15 opened by yihong1120 - 0
Why does this support larger scale images than those trained with the base model?
#49 opened by andupotorac - 1
Segmentation fault (core dumped) error.
#45 opened by trikim - 0
- 0
Network connection problem with the GPT interface
#47 opened by CJT666 - 0
missing openai/clip-vit-large-patch14
#46 opened by LWHYC - 4
Any updates on a ComfyUI solution?
#42 opened by camoody1 - 0
How to disable xformers?
#44 opened by D222097 - 23
Comfy Implementation
#1 opened by ShadoW-Shinigami - 0
SDXL CLIP doesn't support token length over 77
#43 opened by Anmuliar - 1
- 6
support diffusers
#36 opened by akk-123 - 4
TypeError: RegionalDiffusionXLPipeline.__init__() missing 2 required positional arguments: 'text_encoder_2' and 'tokenizer_2'
#41 opened by hq0709 - 1
- 0
Lightning.AI Studio Collaboration: RPG-DiffusionMaster as a Studio Template
#40 opened by Cstrausman89 - 0
- 8
401 Client Error: Unauthorized for url: https://huggingface.co/None/resolve/main/config.json
#11 opened by yzhao30 - 2
Whether to release fine-tuning code
#13 opened by bank010 - 1
It is wrong with gpt4 api?
#37 opened by Seyanliu - 0
- 0
Triton 2.0.0 cannot be installed
#34 opened by 449693691 - 0
- 0
Can you add this to InvokeAI?
#32 opened by PierrunoYT - 2
- 0
RuntimeError: Expected query.size(0) == key.size(0) to be true, but got false
#31 opened by adammenges - 5
24GB VRAM not enough?
#7 opened by JosefKuchar - 1
- 0
On the issue of effectiveness
#30 opened by zhangsdly - 2
- 1
WebUI extension is ready
#28 opened by zydxt - 0
- 2
Why albedobaseXL_v20?
#21 opened by alphacoder01 - 6
- 4
Style database not found: styles.csv
#20 opened by RahulSinghalChicago - 0
Discord
#22 opened by inevitable-2031 - 1
- 1
How to change the resolution?
#16 opened by Subarasheese - 0
- 0
License
#12 opened by fakerybakery - 1
Error loading script: latent.py
#9 opened by yizhangliu - 0
How to use Mini-GPT4?
#10 opened by kaijingxjtu - 6
- 3
Success rate of the MLLM layout output (Colab notebook + example outputs)
#5 opened by ShashwatNigam99