Edit workflow：http://i71i.com/mby8
Register for free and get 1000 points. Log in every day and get points
Perfect Upgrade ，Seamlessly replace the fill model
OneReward is a novel visual domain RLHF approach that significantly improves the generative capabilities of strategy models across multiple subtasks by using Qwen2.5-VL as a generative reward model to enhance multi-task reinforcement learning. Based on OneReward, FLUX.1-Fill-dev-OneReward - Based on FLUX Fill [dev], it surpasses the closed-source FLUX Fill [Pro] in image restoration and epitaxy tasks, providing a powerful new benchmark for future unified image editing research.
------------------------------------------------
Base model:
black-forest-labs/ : Black Forest Labs.
bytedance-research/OneReward: The OneReward model developed by the ByteDance research team for reinforcement learning optimization.
yichengup/flux.1-fill-dev-OneReward: A model developed by yichengup that combines Flux.1-Fill-dev and OneReward, focusing on image filling and scaling tasks.
Label:
flux : Flux series models.
flux-fill : The image fill feature in the Flux series.
onereward: OneReward reinforcement learning methodology.
------------------------------------------------
FLUX.1-Fill-dev is an open-source image restoration and scaling model developed by Black Forest Labs, and the following is its detailed description:
Basic information
Model Architecture: Adopts the Rectified Flow Transformer architecture, combined with the generation capabilities of diffusion models, to intelligently fill in missing areas of images based on text prompts.
Parameter scale: 12 billion parameters.
Training method: Guidance distillation is used to optimize inference speed.
Licensing method: Model weights are publicly available and generated content can be used for personal, scientific, and commercial use, subject to the FLUX.1 [dev] Non-Commercial License.
Core features:
Image restoration: It can fill in missing or removed areas in the image based on text descriptions and binary masks, achieving high-precision image restoration.
Image Expansion: Support for outpainting, which seamlessly expands the boundaries of existing images.
Text Understanding and Generation: Understand complex text instructions and combine them with image context to generate natural, coherent restoration results.
Description
Edit workflow：http://i71i.com/mby8
Register for free and get 1000 points. Log in every day and get points
OneReward is a novel visual domain RLHF approach that significantly improves the generative capabilities of strategy models across multiple subtasks by using Qwen2.5-VL as a generative reward model to enhance multi-task reinforcement learning. Based on OneReward, FLUX.1-Fill-dev-OneReward - Based on FLUX Fill [dev], it surpasses the closed-source FLUX Fill [Pro] in image restoration and epitaxy tasks, providing a powerful new benchmark for future unified image editing research.
------------------------------------------------
Base model:
black-forest-labs/ : Black Forest Labs.
bytedance-research/OneReward: The OneReward model developed by the ByteDance research team for reinforcement learning optimization.
yichengup/flux.1-fill-dev-OneReward: A model developed by yichengup that combines Flux.1-Fill-dev and OneReward, focusing on image filling and scaling tasks.
Label:
flux : Flux series models.
flux-fill : The image fill feature in the Flux series.
onereward: OneReward reinforcement learning methodology.
------------------------------------------------
FLUX.1-Fill-dev is an open-source image restoration and scaling model developed by Black Forest Labs, and the following is its detailed description:
Basic information
Model Architecture: Adopts the Rectified Flow Transformer architecture, combined with the generation capabilities of diffusion models, to intelligently fill in missing areas of images based on text prompts.
Parameter scale: 12 billion parameters.
Training method: Guidance distillation is used to optimize inference speed.
Licensing method: Model weights are publicly available and generated content can be used for personal, scientific, and commercial use, subject to the FLUX.1 [dev] Non-Commercial License.
Core features:
Image restoration: It can fill in missing or removed areas in the image based on text descriptions and binary masks, achieving high-precision image restoration.
Image Expansion: Support for outpainting, which seamlessly expands the boundaries of existing images.
Text Understanding and Generation: Understand complex text instructions and combine them with image context to generate natural, coherent restoration results.
FAQ
Comments (12)
这个是抱脸上转载的还是经过自己微调的呀
转载。我看这边没有就传上来了
where is the face_yolov8m folder for Layermask: Object Detector YOLOV8 Advance ? i downloaded the model but i dont know where it goes
solution : Create a folder with name "yolo" in the Models folder and place it there
@Bonticarius Well done!
Works perfect after a few tweaks thank s!
I'm very happy to be able to help you. Have fun
hey can you tell me what tweaks you made? im having problems with there being just noise in the cropped face instead of it generating the new face! was just wandering if your tweaks may help my situation. Thankyou
@dkpc69 make sure you download all the correct loras.clip vision, style model, and the yolov8m model
@Bonticarius Thanks for the reply diddnt realise you messaged back! Unfortunately I still couldn’t get it going right, I’ll just stick to qwen edit! Thanks though
Maybe I'm missing something, but when I try the link for the workflow I get the error message
Access to i71i.com was denied
You don't have authorization to view this page.
HTTP ERROR 403
When you get a chance, can you fix the Workflow link?
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.