👍 Please Rate! - Your feedback, rating or a follow are greatly appreciated. - Thankyou! 😊
🦴 Any yellow Buzz donated to this model will go toward making it freely available for On-Site Generation.🦴
Frisky Dingo🐕 is a hybrid model that blends IL composition with XL Photorealistic outputs.
(also works well as a refiner).
This is a hybrid with a heavily IL biased CLIP, (primarily iLustMix v7), & an XL biased UNET. It can use IL, XL & PONY LORAs to varying degrees, though you may need to adjust the weights a bit, (situationally depending). Poses and concepts tend to work well while things like artist styles generally don't translate to realism, but can still be compositionally useful, in addition to pushing the model into a semi-realism or illustration / anime style. (I'll have a section @ the bottom for additional notes on prompting, LORAs & settings which I'll try to expand on it over time).
V2 gallery images were rendered in a single pass at 2048 x 1536 using the Kohya Deep Shrink Node, some also use PAG. Load any gallery image in ComfyUI to get the workflow.
V1 used upscaling & a detailer in most example images, (4x_RealWebPhoto-v4 and / or 4x_foolhardy_Remacri).
V2 Suggested settings:
• VAE: sdxl_vae (baked in).
• Clip skip: 2 was used during merge.
• Samplers/Schedulers: A fairly wide range of sample / scheduler combos are supported. for more complex shots, full body with hands etc. (DPM++ 3M SDE_GPU / SGM_Uniform will generally yield the best results). Several other options can provide better results, depending on the scenario.
• low step options: (LCM/SGM_Uniform or DPM++ 2M/AYS, DPM++2Sa/AYS).
• Resolution: Resolution: up to 2048 x 1536, with the Kohya Deep Shrink node, portrait or landscape. all standard 1MP resolutions work well.
• CFG: 3.5 - 6.5 (I typically use 4.6, - 5.6)
• Steps: 30 - 36
• DMD2 / LCM: I like to set the LORA strength low (around 0.6) & the CFG high (about 1.6-1.7) with 12-16 steps. This allows neg prompts to work & I find it to