This is early experimental LoRa for researching borders of training the concept of strict mirror.I think it is possible because SDXL can draw mirror floors.<h2 id="status-3nkor43w2">Status</h2>IL V2: this LoRa version can increase probability (+24% for 8-20 steps) of getting strict reflections in a new generation. Increasing steps is refining the results. Increasing LoRa's weight can refine the results (60% success with weight=2.0).IL V1: this LoRa version can slightly increase probability (+10% for 4 dmd2-steps, +12-16% for 8 dmd2-steps) to find strict reflections in a new generation. Increasing steps is refining the results.I go to the next step of the experiment.<h2 id="changelog-qx4qz9fgh">Changelog</h2><h3 id="il-v2-imi4bk1a1">IL V2</h3><ul><li>Added negative tokens:<ul><li>x_out_of_mirror (protects against a reflection outside mirror's bounds)</li><li>x_differect_reflection (supress a wrong symmetry)</li><li>different reflection (same the x_out_of_mirror but danbooru tag)</li></ul></li><li>Added ai-generated images with negative tokens to dataset.</li><li>60 epochs instead of 10 epochs of version 1</li><li>Trained with cleaned dictionary: x_mirror_reflection, x_reflection_face, x_reflection_facing_aside, x_reflection_facing_away, reflection, mirror, hand on mirror, full-length mirror, broken mirror, reflection focus, looking at mirror.</li></ul><h2 id="usage-5k4r5sqmi">Usage</h2>Connect LoRa in your workflow and then activate by word x_mirror_reflection in your prompt. Next choose one of these controls for the position of the character's face relative to the mirror:<ul><li>x_reflection_facing_away</li><li>x_reflection_facing_aside</li><li>x_reflection_face</li></ul>Now you can use negative prompt (+8% to find good mirroring in IL V2): x_out_of_mirror, x_differect_reflection, different reflection

Strict mirroring

VERSION 2CHANGE LOG<ul><li>Added negative tokens:<ul><li>x_out_of_mirror (protects against a reflection outside mirror's bounds)</li><li>x_differect_reflection (supress a wrong symmetry)</li><li>different reflection (same the x_out_of_mirror but danbooru tag)</li></ul></li><li>Added ai-generated images with negative tokens to dataset.</li><li>60 epochs instead of 10 epochs of version 1</li><li>Trained with cleaned dictionary: x_mirror_reflection, x_reflection_face, x_reflection_facing_aside, x_reflection_facing_away, reflection, mirror, hand on mirror, full-length mirror, broken mirror, reflection focus, looking at mirror.</li></ul>--------------------------TESTS--------------------------holy mix illustrous, spo, dmd2, 8 steps, 1 cfg, with mirror lora, 25 runs--------------------------pos. prompt:--------------------------masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest,1girl, solo,(((x_mirror_reflection))), reflection, mirror,{||hand on mirror},{|||full-length mirror},{||broken mirror}{||reflection focus},{x_reflection_face, looking at mirror|x_reflection_facing_aside, {looking at viewer|looking at another|looking back, looking to the side, facing away}|x_reflection_facing_away, {looking at viewer|looking at another|looking back, looking to the side, facing away}}--------------------------32% - strict reflection16% - strict reflection but outside mirror borders48% - wrong symmetry4% - trash (prompt misunderstanding)----------------------------------------------------holy mix illustrous, spo, dmd2, 8 steps, 1 cfg, no mirror lora, 25 runs,--------------------------pos. prompt: same--------------------------8% - strict reflection4% - strict reflection but outside mirror borders56% - wrong symmetry32% - trash (prompt misunderstanding)----------------------------------------------------holy mix illustrous, spo, 20 steps, 6 cfg, with mirror lora, 25 runs,--------------------------pos. prompt: sameneg. prompt: x_out_of_mirror, x_differect_reflection, different reflection--------------------------40% - strict reflection16% - strict reflection but outside mirror borders40% - wrong symmetry4% - trash (prompt misunderstanding)----------------------------------------------------holy mix illustrous, spo, 20 steps, 6 cfg, without mirror lora, 25 runs,--------------------------pos. prompt: sameneg. prompt: same--------------------------16% - strict reflection0% - strict reflection but outside mirror borders16% - wrong symmetry68% - trash (prompt misunderstanding)--------------------------Hypothesis: lora weight x2 can refine results.-----------------------------Illustrous, spo, dmd2, 8 steps, 1.5 cfg, with mirror lora, 25 runs--------------------------pos. prompt: sameneg. prompt: same--------------------------32% - strict reflection20% - strict reflection but outside mirror borders36% - wrong symmetry12% - trash (prompt misunderstanding)-------------------------------------------------------Illustrous, spo, dmd2, 8 steps, 1.5 cfg, without mirror lora, 25 runs--------------------------pos. prompt: sameneg. prompt: same--------------------------12% - strict reflection0% - strict reflection but outside mirror borders32% - wrong symmetry56% - trash (prompt misunderstanding)-------------------------------------------------------Illustrous, spo, dmd2, 8 steps, 1.5 cfg, with mirror lora x2 strength, 25 runs--------------------------pos. prompt: sameneg. prompt: same--------------------------60% - strict reflection2% - strict reflection but outside mirror borders36% - wrong symmetry0% - trash (prompt misunderstanding)-------------------------------------------------------Illustrous, spo, dmd2, 8 steps, 1.5 cfg, with mirror lora x3 strength, 50 runs--------------------------pos. prompt: sameneg. prompt: same--------------------------36% - strict reflection0% - strict reflection but outside mirror borders62% - wrong symmetry2% - trash (prompt misunderstanding)and dramatically low quality of all results in this batch.--------------------------SUMMARY<ul><li>This version increases probability of getting strict mirroring by 24%.</li><li>Negative prompt increases probability of getting strict mirroring by 8%.</li><li>Try to increase LoRa weight.</li><li>High LoRa weight (&gt;2) spoils results.</li></ul>

Strict_mirroring_v2.safetensors

IL V2

IL V1

This is early experimental LoRa for researching borders of training the concept of strict mirror.I think it is possible because SDXL can draw mirror floors.StatusIL V2: this LoRa version can increase probability (+24% for 8-20 steps) of getting strict reflections in a new generation. Increasing steps is refining the results.IL V1: this LoRa version can slightly increase probability (+10% for 4 dmd2-steps, +12-16% for 8 dmd2-steps) to find strict reflections in a new generation. Increasing steps is refining the results.I go to the next step of the experiment.ChangelogIL V2<ul><li>Added negative tokens:<ul><li>x_out_of_mirror (protects against a reflection outside mirror's bounds)</li><li>x_differect_reflection (supress a wrong symmetry)</li><li>different reflection (same the x_out_of_mirror but danbooru tag)</li></ul></li><li>Added ai-generated images with negative tokens to dataset.</li><li>60 epochs instead of 10 epochs of version 1</li><li>Trained with cleaned dictionary: x_mirror_reflection, x_reflection_face, x_reflection_facing_aside, x_reflection_facing_away, reflection, mirror, hand on mirror, full-length mirror, broken mirror, reflection focus, looking at mirror.</li></ul>UsageConnect LoRa in your workflow and then activate by word x_mirror_reflection in your prompt. Next choose one of these controls for the position of the character's face relative to the mirror:<ul><li>x_reflection_facing_away</li><li>x_reflection_facing_aside</li><li>x_reflection_face</li></ul>Now you can use negative prompt (+8% to find good mirroring in IL V2): x_out_of_mirror, x_differect_reflection, different reflectionTrigger Wordsx_mirror_reflectionx_reflection_facing_awayx_reflection_facing_asidex_reflection_face

Files with SHA256: 4c5cd52ba6f1744398368db67fb8bee88990b9e27ef14ef4d1bc03c4c1d9d237