Instructions to use Yitaallen/keepedit-release-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Yitaallen/keepedit-release-weights with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Yitaallen/keepedit-release-weights") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
KeepEdit Release LoRA Weights
本仓库只存放 KeepEdit 发布版 LoRA 权重,不包含 Qwen-Image-Edit-2511 基座模型。
目录结构:
qwen_edit_2511_keepedit_gt_onestage/
step-4404.safetensors
qwen_edit_2511_mtp_phasea/
step-2269.safetensors
qwen_edit_2511_moe_teacher_onestage/
step-2202.safetensors
三个 LoRA 的推理条件完全一致:
source image + instruction -> edited image
推理时不需要 target、mask、专家候选图或 MoE teacher 图。
下载到项目目录:
huggingface-cli download <WEIGHTS_REPO_ID> \
--repo-type model \
--local-dir checkpoints \
--local-dir-use-symlinks False
随后可运行:
EXPERIMENT_NAME=qwen2511_gt_onestage \
LORA_PATH=checkpoints/qwen_edit_2511_keepedit_gt_onestage \
bash scripts/evaluate_qwen_edit_experiment.sh
EXPERIMENT_NAME=qwen2511_mtp_phasea \
LORA_PATH=checkpoints/qwen_edit_2511_mtp_phasea \
bash scripts/evaluate_qwen_edit_experiment.sh
EXPERIMENT_NAME=qwen2511_moe_teacher_onestage \
LORA_PATH=checkpoints/qwen_edit_2511_moe_teacher_onestage \
bash scripts/evaluate_qwen_edit_experiment.sh
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support