I trained this lora on 25 images of Emma Watson for 1600 steps, enjoy :D
v1.2 improved quality, no trigger required. This is the same model I posted on huggingface a few days ago.
v1.1 updated the model to require the trigger emmwat, after training extensively on triggers, using the person's name reduces model accuracy. please let me know if you prefer the model trigger or not. thanks ^^
v1.0 does not require a trigger word
Below is my flux LORA training guide:
https://civarchive.com/articles/6678
Description
FAQ
Comments (4)
I dont get it - using ForgeUI + flux1.dev nf4 (2070 Super) I dont get Emmas face on the character. It seems like the Prompt is ignoring my decission...
you wrote: "no trigger required" but if no trigger required how to tell the process to use her Face (I put her file into "models" - "Lora"
where can I find your workflow?
hii, my ComfyUI workflow is below. to make the lora work, you need to load the lora with the LoadLora node.
https://civitai.com/models/632945?modelVersionId=768534
In Forge, make sure you're up-to-date, and in the "Diffusion in Low Bits" option, set it to bnb-nf4 (fp16 LoRA)
Amazing!!!...Can you please do Marzia Kjellberg
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.