Use 'sw33ny' to activate the lora.
There are two versions available, Base Pony and Pony Realism.
Pony Realism is trained on Pony Realism and would give best results on realistic models.
The second version is trained on vanilla Pony and is not as accurate but works on all pony models.
If you enjoy my work please leave a like or a review. Pics of your work are also appreciated :)
Description
FAQ
Comments (10)
I'm not used to ComfyUI and it's my second week trying out Flux. I can't get it to work. Even when I copy a full node layout based on an existing image, I get all the elements in the result, but the face has nothing to do with Sidney. What else do I need besides this lora and Flux.D? Thanks!
Make sure both comfyui and the nodes are up to date. I also struggled with it and then found out my lora node wasn't updated. There an option to update the nodes in the manager.
I also had this issue overall till someone mentioned that I needed a full reinstall of my ComfyUI, Pytorch, and dependencies. Turns out, there's was something wrong/off with the ComfyUI programming that wasn't letting flux Loras work. My original ComfyUI install wasn't even two weeks old at that point and still needed the reinstall.
@Nigredex Hi! Thanks for your answer. I got it to work, but only using fp8_e4m3fn as weight_dtype and StableDiffusion3SD3_TextEncoderT5E4m3fn in dual clip loader along with the clip_I from FLUX. If I switch to fp16, the face is totally different. Could you make it work with the fp16 version?
Can you please tell me what program you used to train this new model? How many source images and steps were there?
I followed this guide Training a flux LoRA using SimpleTuner on RunPod | Civitai
Great resemblance! Would you do Alexa Demie too?
@cynicalxrose Not planned at the moment, if you got a high res dataset I can put in the to do list
Need help making this lora woke, tried everything, updated comfy and all nodes and still can’t get it, if anyone could lend me some advice or share there workflow that would be greatly appreciated.
You can drag the image to comfy to get the workflow, there was a breaking change in comfy about two weeks ago. If yours is older a fresh install might fix it
Details
Files
sydneySweeneyFlux.safetensors
Mirrors
sydneySweeneyFlux.safetensors
sydneySweeneyFlux.safetensors
Model_sydneySweeneyFlux.safetensors
lora.safetensors
sydneySweeneyFlux.safetensors
sydneySweeneyFlux.safetensors
sydneySweeneyFlux.safetensors
sydneySweeneyFlux.safetensors
640572_sydneySweeneyFlux.safetensors
lora (3).safetensors
sydneySweeneyFlux.safetensors
sydneySweeneyFlux.safetensors
lora (3).safetensors
lora (3).safetensors
lora (3).safetensors
lora (3).safetensors
sw33ny.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.