Skip to content

Issues: XLabs-AI/x-flux

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

88 Open 24 Closed
88 Open 24 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Save memory for training？
#132 opened Oct 30, 2024 by StarsTesla
bug for ip adapter v2
#131 opened Oct 29, 2024 by ZivKidd
2
training of the ip adapter
#130 opened Oct 28, 2024 by garychan22
Is it possible to run with multiple LORAs?
#129 opened Oct 28, 2024 by 4ku
Load Flux Lora
#128 opened Oct 25, 2024 by giusparsifal
any readings about how these ipadapter,lora,controlnet is added to the diffusion transformers?
#127 opened Oct 25, 2024 by flankechen
How much vram needed for finetuning (full parameter fine tuning, not lora)
#126 opened Oct 23, 2024 by Adoni
Missing Keys double_block error when fine tuning ControlNet and Lora.
#125 opened Oct 18, 2024 by niqbal996
how to understand the num(guidance)=4 with the code , guidance_vec = torch.full((x_t.shape[0],), 4, device=x_t.device, dtype=x_t.dtype)
#124 opened Oct 18, 2024 by aiXia121
about controlnet's condition image
#121 opened Oct 11, 2024 by oukohou
True cfg and the choice of guidance scale during inference
#120 opened Oct 8, 2024 by ZYM-PKU
Cannot reproduce the example results of IP Adapter
#119 opened Sep 26, 2024 by aihao2000
x_t = (1 - t) * x_1 + t * x_0
#117 opened Sep 25, 2024 by aiXia121
1
Could x-flux run on RTX 3090?
#115 opened Sep 24, 2024 by xingyouxin
4
Timesteps different from the original BFL's implementation?
#114 opened Sep 19, 2024 by dkenw
Lora + Controlnet
#113 opened Sep 18, 2024 by fefespn
Number of controlnet blocks
#112 opened Sep 18, 2024 by bjtuln
1
Questions Regarding Training Costs, Dtype Error on H100, and ControlNet Loss Behavior
#111 opened Sep 17, 2024 by zyyyz
NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
#109 opened Sep 12, 2024 by HuiZhang0812
(out of memory)OOM for traing controlnet on flux-dev-fp8 on A100 40G
#108 opened Sep 11, 2024 by kongzijian
6
Error when train controlnet using multi GPU
#107 opened Sep 10, 2024 by 1goodone
3
Requesting feature for latent caching.
#106 opened Sep 9, 2024 by aravindhv10
1
How to use multi gpu to run main.py with ip adapter?
#105 opened Sep 9, 2024 by Vova-B
Cannot access gated repo for url https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors.
#103 opened Sep 6, 2024 by szhao1968
2
Broadcasting issue when using training batch size > 1
#102 opened Sep 5, 2024 by aravindhv10
2
ProTip! What’s not been updated in a month: updated:<2024-10-01.