--- language: - en license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - safetensors #inference: true #thumbnail: https://s2.loli.net/2023/05/31/bl27yWANrT3asoG.png #widget: #- text: >- # 1girl with blonde two side up disheveled hair red eyes in black serafuku red # ribbon, upper body, simple background, grey background, collarbone # example_title: example 1girl #datasets: #- Crosstyan/BPDataset library_name: diffusers --- # BPModel (and other models)'s UNET merged into SD 1.4 # ![230910-1370168022-768-768-11-48-20230910230212.png](https://huggingface.co/6DammK9/bpmodel-sd14-merge/resolve/main/230910-1370168022-768-768-11-48-20230910230212.png) ``` parameters (ushanka:0.98), [[braid]], [[astolfo]], [[[[moscow, russia]]]], [[[[[[snow]]]]]] Negative prompt: (bad:0), (comic:0), (cropped:0), (error:0), (extra:0), (low:0), (lowres:0), (speech:0), (worst:0) Steps: 48, Sampler: Euler, CFG scale: 11, Seed: 1370168022, Size: 768x768, Model hash: 4a15b47ed1, Model: bp_nman_e29-sd_14, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Clip skip: 2, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, Version: v1.6.0 ``` ## Self explained. ## - [BPModel](https://huggingface.co/Crosstyan/BPModel/tree/main) is a model intentionally preserved its UNET, *and dropped all the others, especially Text Encoder and VAE*. [PR has been made](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/7523), and it never get entertained. Workaround (Switch to SD 1.4 and then BPModel) works fine, [until I have some other use for it.](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README.MD) - I need to align all the models I want to merge before I start merging them, to ensure *preserving the original Text Encoder will maximize the variance of the generation.* ## Why SD 1.4 ## - "*It is by design."* - Not author, quote lost long ago - To verify, [head to my artwork long ago and try to replicate.](https://www.pixiv.net/en/artworks/104582308) *I made a more fancy version of him because dynamic CFG OP* ## Models to be merged ## - See [Files.](https://huggingface.co/6DammK9/bpmodel-sd14-merge/tree/main) - [Full list in Github](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README.MD#merging-models-from-different-background) - [VBP](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch02/f59359c175.md): `VBP23-1024-ep49-sd-v1-4` - [CBP](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch02/ae2b38ac14.md): `cbp2-e60-sd-v1-4` - [mzpikas_tmnd_enhanced](https://huggingface.co/ashen-sensored/mzpikas_tmnd_enhanced): `mzpikas_tmnd_enhanced-sd-v1-4` - [DreamShaperV8](https://civitai.com/models/4384/dreamshaper): `dreamshaper_8-sd-v1-4` - [CoffeeWithLiquor](https://huggingface.co/StereoBartender/CoffeeWithLiquor): `CoffeeWithLiquor-sd-v1-4` - [BreakDomain](https://civitai.com/models/117192/breakdomainowners-model-i-have-no-rights-if-he-want-it-will-be-taken-down): `breakdomain-A0440-sd-v1-4` - [AIWMix](https://civitai.com/models/74165?modelVersionId=78888): `aiwmix-sd-v1-4` - [Ether Blu Mix](https://civitai.com/models/17427/ether-blu-mix): `etherBluMix5-sd-v1-4` - [MajicMix](https://civitai.com/models/43331?modelVersionId=94640):`majicmixRealistic_v6-sd-v1-4` - [Silicon29](https://huggingface.co/Xynon/SD-Silicon): `Silicon29-sd` ## Models may be merged ## - [BPModel](https://huggingface.co/Crosstyan/BPModel): `bp_nman_e29-sd-v1-4` - [ALunarDream](https://discord.com/channels/930499730843250783/1087111248447017172/1087111248447017172): *Coming soon* - [AIDv2.10](https://civitai.com/models/16828/aidv210-anime-illust-diffusion): *Coming soon* ## Experimental Merges ## - *Swapping TE back with original model*. See [AstolfoMix.](https://huggingface.co/6DammK9/AstolfoMix/blob/main/README.md) - 08 with CoffeeWithLiquor: `08-vcbpmt_d8cwlbd_aweb5-cwl` ![xyz_grid-0106-978318572-3072-1012-4.5-48-20230922003223.png](https://huggingface.co/6DammK9/bpmodel-sd14-merge/resolve/main/xyz_grid-0106-978318572-3072-1012-4.5-48-20230922003223.png) ``` parameters (aesthetic:0), (quality:0), (solo:0), (1girl:0), (gawr_gura:0.98) Negative prompt: (worst:0), (low:0), (bad:0), (exceptional:0), (masterpiece:0), (comic:0), (extra:0), (lowres:0) Steps: 48, Sampler: Euler, CFG scale: 4.5, Seed: 978318572, Size: 768x768, Model hash: d94d7363a0, Model: 08-vcbpmt_d8cwlbd_aweb5-cwl, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Clip skip: 2, Version: v1.6.0 ``` ## License ## This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies: 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license 3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license [here](https://huggingface.co/spaces/CompVis/stable-diffusion-license/blob/main/license.txt)