<h3 id="hunyuan-v1.0-:-d6awfv8e4">HUNYUAN v1.0 :</h3>Trained on Hunyuan Video fp8 with 512x512 px with 68 photos of Natalie Dormer with detailed GPT-4 captions. Tested on Hunyuan Video fp8 and Fast Hunyuan Video fp8 ! No keywords needed. Use around Lora strength=1.1.embedded_guidance_scale= 5.0-8.0 and flow_shift=7.0-12.0:Positive : {Short summary of the scene e.g. Professional video of a blonde woman giving and interview on the red carpet}, {more detailed scene and background description}, {lighting description}, {camera direction e.g. panning in, panning out, zoom in etc.},&lt;lora:natdormer_hunyuan_epoch42:1.1&gt;<h3 id="flux-v1.0-:-darz1yyhu">FLUX v1.0 :</h3><h2 id="please-donate-buzz-for-flux-lora-training-!-5k0f6w39p">Please Donate Buzz for FLUX Lora Training !</h2>Trained on FLUX.1 [dev] with 196 photos of Natalie Dormer. Tested on FLUX 1.D (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.8-1.2. No keywords needed! Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:Positive : {Artstyle, Character and scene description in usual FLUX fashion}, &lt;lora:Natalie_Dormer_FLUX_v1_r1-000016:1&gt;<h3 id="sdxl-v3.0-:-txwlxw53q">SDXL v3.0 :</h3>Trained on Juggernaut X with 196 photos of Natalie Dormer . Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "natxdormer" . Use around strength 1.0. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:Positive : {Artstyle}, {Character and scene description}, natxdormer, &lt;lora:natdormer_juggerX_xl_1_wocap_merger_62_136_03_07-natxdormer:1&gt;Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child<h3 id="sdxl-v2.0-80mb-:-p5kxyrn82">SDXL v2.0 80mb :</h3>Retrained on 115 images of Natalie Dormer with a new Lora setting for one-fourth the size while maintaining likeness. Use with keyword : "natxdormer". Lora strength with keyword should be around 0.8-1.2.<h3 id="sdxl-v1.0-:-1rge8k7jr">SDXL v1.0 :</h3>Lora trained on 196 high quality photos of Natalie Dormer on the SDXL 1.0 base model. The recommended Lora strength for most use cases is between 0.8-1.2.

Natalie Dormer (HUNYUAN + FLUX + SDXL)

HUNYUAN v1.0 :Trained on Hunyuan Video fp8 with 512x512 px with 68 photos of Natalie Dormer with detailed GPT-4 captions. Tested on Hunyuan Video fp8 and Fast Hunyuan Video fp8 ! No keywords needed. Use around Lora strength=1.1.embedded_guidance_scale= 5.0-8.0 and flow_shift=7.0-12.0:Positive : {Short summary of the scene e.g. Professional video of a blonde woman giving and interview on the red carpet}, {more detailed scene and background description}, {lighting description}, {camera direction e.g. panning in, panning out, zoom in etc.},&lt;lora:natdormer_hunyuan_epoch42:1.1&gt;

Files with SHA256: 92fa5ede580cc669ca58ed916c5c9c36104562ce083962d177d1c83b73b40499