diff --git a/.gitattributes b/.gitattributes index 886ac0c..54b765c 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,38 +1,38 @@ *.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text -*.bin.* filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text -*.zstandard filter=lfs diff=lfs merge=lfs -text -*.tfevents* filter=lfs diff=lfs merge=lfs -text -*.db* filter=lfs diff=lfs merge=lfs -text -*.ark* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text -*.safetensors filter=lfs diff=lfs merge=lfs -text -*.ckpt filter=lfs diff=lfs merge=lfs -text -*.gguf* filter=lfs diff=lfs merge=lfs -text -*.ggml filter=lfs diff=lfs merge=lfs -text -*.llamafile* filter=lfs diff=lfs merge=lfs -text -*.pt2 filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +T2I.png filter=lfs diff=lfs merge=lfs -text +inpaint.png filter=lfs diff=lfs merge=lfs -text +diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index bef6db2..a183724 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,82 @@ --- -license: Apache License 2.0 - -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt - -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm +license: other +license_name: flux-1-dev-non-commercial-license +license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md +language: +- en +base_model: black-forest-labs/FLUX.1-dev +library_name: diffusers +tags: +- Text-to-Image +- FLUX +- Stable Diffusion +pipeline_tag: text-to-image --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 -SDK下载 -```bash -#安装ModelScope -pip install modelscope -``` -```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('alimama-creative/FLUX.1-Turbo-Alpha') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/alimama-creative/FLUX.1-Turbo-Alpha.git +
+ alibaba + alimama +
+ +[中文版Readme](./README_ZH.md) + +This repository provides a 8-step distilled lora for [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) model released by AlimamaCreative Team. + +# Description +This checkpoint is a 8-step distilled Lora, trained based on FLUX.1-dev model. We use a multi-head discriminator to improve the distill quality. Our model can be used for T2I, inpainting controlnet and other FLUX related models. The recommended guidance_scale=3.5 and lora_scale=1. Our Lower steps version will release later. + +- Text-to-Image. + +![](./images/T2I.png) + +- With [alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta](https://huggingface.co/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta). Our distilled lora can be well adapted to the Inpainting controlnet, and the accelerated generated effect can follow the original output well. + +![](./images/inpaint.png) + +# How to use +## diffusers +This model can be used ditrectly with diffusers + +```json +import torch +from diffusers.pipelines import FluxPipeline + +model_id = "black-forest-labs/FLUX.1-dev" +adapter_id = "alimama-creative/FLUX.1-Turbo-Alpha" + +pipe = FluxPipeline.from_pretrained( + model_id, + torch_dtype=torch.bfloat16 +) +pipe.to("cuda") + +pipe.load_lora_weights(adapter_id) +pipe.fuse_lora() + +prompt = "A DSLR photo of a shiny VW van that has a cityscape painted on it. A smiling sloth stands on grass in front of the van and is wearing a leather jacket, a cowboy hat, a kilt and a bowtie. The sloth is holding a quarterstaff and a big book." +image = pipe( + prompt=prompt, + guidance_scale=3.5, + height=1024, + width=1024, + num_inference_steps=8, + max_sequence_length=512).images[0] ``` -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +## comfyui + +- T2I turbo workflow: [click here](./workflows/t2I_flux_turbo.json) +- Inpainting controlnet turbo workflow: [click here](./workflows/alimama_flux_inpainting_turbo_8step.json) + + +# Training Details + +The model is trained on 1M open source and internal sources images, with the aesthetic 6.3+ and resolution greater than 800. We use adversarial training to improve the quality. Our method fix the original FLUX.1-dev transformer as the discriminator backbone, and add multi heads to every transformer layer. We fix the guidance scale as 3.5 during training, and use the time shift as 3. + +Mixed precision: bf16 + +Learning rate: 2e-5 + +Batch size: 64 + +Image size: 1024x1024 \ No newline at end of file diff --git a/README_ZH.md b/README_ZH.md new file mode 100644 index 0000000..fdb97e7 --- /dev/null +++ b/README_ZH.md @@ -0,0 +1,81 @@ +--- +license: other +license_name: flux-1-dev-non-commercial-license +license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md +language: +- en +base_model: black-forest-labs/FLUX.1-dev +library_name: diffusers +tags: +- Text-to-Image +- FLUX +- Stable Diffusion +pipeline_tag: text-to-image +--- + +
+ alibaba + alimama +
+ +本仓库包含了由阿里妈妈创意团队开发的基于[FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev)模型的8步蒸馏版。 + +# 介绍 + +该模型是基于FLUX.1-dev模型的8步蒸馏版lora。我们使用特殊设计的判别器来提高蒸馏质量。该模型可以用于T2I、Inpainting controlnet和其他FLUX相关模型。建议guidance_scale=3.5和lora_scale=1。我们的更低步数的版本将在后续发布。 + +- Text-to-Image. + +![](./images/T2I.png) + +- 配合[alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta](https://huggingface.co/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta)。我们模型可以很好地适配Inpainting controlnet，并与原始输出保持相似的结果。 + +![](./images/inpaint.png) + +# 使用指南 +## diffusers +该模型可以直接与diffusers一起使用 + +```python +import torch +from diffusers.pipelines import FluxPipeline + +model_id = "black-forest-labs/FLUX.1-dev" +adapter_id = "alimama-creative/FLUX.1-Turbo-Alpha" + +pipe = FluxPipeline.from_pretrained( + model_id, + torch_dtype=torch.bfloat16 +) +pipe.to("cuda") + +pipe.load_lora_weights(adapter_id) +pipe.fuse_lora() + +prompt = "A DSLR photo of a shiny VW van that has a cityscape painted on it. A smiling sloth stands on grass in front of the van and is wearing a leather jacket, a cowboy hat, a kilt and a bowtie. The sloth is holding a quarterstaff and a big book." +image = pipe( + prompt=prompt, + guidance_scale=3.5, + height=1024, + width=1024, + num_inference_steps=8, + max_sequence_length=512).images[0] +``` + +## comfyui + +- 文生图加速链路: [点击这里](./workflows/t2I_flux_turbo.json) +- Inpainting controlnet 加速链路: [点击这里](./workflows/alimama_flux_inpainting_turbo_8step.json) + + +# 训练细节 + +该模型在1M公开数据集和内部源图片上进行训练，这些数据美学评分6.3+而且分辨率大于800。我们使用对抗训练来提高质量，我们的方法将原始FLUX.1-dev transformer固定为判别器的特征提取器，并在每个transformer层中添加判别头网络。在训练期间，我们将guidance scale固定为3.5，并使用时间偏移量3。 + +混合精度: bf16 + +学习率: 2e-5 + +批大小: 64 + +训练分辨率: 1024x1024 \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..b5f6ce7 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-to-image", "allow_remote": true} \ No newline at end of file diff --git a/diffusion_pytorch_model.safetensors b/diffusion_pytorch_model.safetensors new file mode 100644 index 0000000..902d354 --- /dev/null +++ b/diffusion_pytorch_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f7523a5e9c3da6cfc730c6b07461129fa52997ea06168e9ed5312228aa0bff +size 694082424 diff --git a/images/T2I.png b/images/T2I.png new file mode 100644 index 0000000..6a42971 --- /dev/null +++ b/images/T2I.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b519e6578c674441c24edf6cea01203d5acae8a151135269cc6636135a55203e +size 9955906 diff --git a/images/images_alibaba.png b/images/images_alibaba.png new file mode 100644 index 0000000..244e9cc Binary files /dev/null and b/images/images_alibaba.png differ diff --git a/images/images_alimama.png b/images/images_alimama.png new file mode 100644 index 0000000..99a2c98 Binary files /dev/null and b/images/images_alimama.png differ diff --git a/images/inpaint.png b/images/inpaint.png new file mode 100644 index 0000000..9425706 --- /dev/null +++ b/images/inpaint.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfdacf1ada0c208a2bc3c536de58fe7d111f118cde16a6bad9409eacaee02124 +size 7228772 diff --git a/workflows/alimama_flux_inpainting_turbo_8step.json b/workflows/alimama_flux_inpainting_turbo_8step.json new file mode 100644 index 0000000..c7322bf --- /dev/null +++ b/workflows/alimama_flux_inpainting_turbo_8step.json @@ -0,0 +1,1666 @@ +{ + "last_node_id": 146, + "last_link_id": 238, + "nodes": [ + { + "id": 88, + "type": "Reroute", + "pos": { + "0": 156.76731872558594, + "1": -115.1278305053711 + }, + "size": [ + 75, + 26 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 223, + "label": "" + } + ], + "outputs": [ + { + "name": "", + "type": "CLIP", + "links": [ + 147, + 210 + ], + "slot_index": 0, + "label": "" + } + ], + "properties": { + "showOutputText": false, + "horizontal": false + } + }, + { + "id": 89, + "type": "Reroute", + "pos": { + "0": 155.76731872558594, + "1": -64.12783813476562 + }, + "size": [ + 75, + 26 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 150, + "label": "" + } + ], + "outputs": [ + { + "name": "", + "type": "VAE", + "links": [ + 151, + 207 + ], + "slot_index": 0, + "label": "" + } + ], + "properties": { + "showOutputText": false, + "horizontal": false + } + }, + { + "id": 72, + "type": "CLIPTextEncodeFlux", + "pos": { + "0": 635.7671508789062, + "1": -120.12781524658203 + }, + "size": { + "0": 219.3687286376953, + "1": 108 + }, + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 147, + "label": "clip" + }, + { + "name": "t5xxl", + "type": "STRING", + "link": 199, + "widget": { + "name": "t5xxl" + }, + "label": "t5xxl" + }, + { + "name": "clip_l", + "type": "STRING", + "link": 200, + "widget": { + "name": "clip_l" + }, + "label": "clip_l" + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 208 + ], + "slot_index": 0, + "shape": 3, + "label": "CONDITIONING" + } + ], + "properties": { + "Node name for S&R": "CLIPTextEncodeFlux" + }, + "widgets_values": [ + "", + "", + 3.5 + ] + }, + { + "id": 131, + "type": "CLIPTextEncodeFlux", + "pos": { + "0": 897.7671508789062, + "1": -151.12783813476562 + }, + "size": { + "0": 222.8309326171875, + "1": 160 + }, + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 210, + "label": "clip" + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 209 + ], + "slot_index": 0, + "shape": 3, + "label": "CONDITIONING" + } + ], + "properties": { + "Node name for S&R": "CLIPTextEncodeFlux" + }, + "widgets_values": [ + "", + "bad,ugly,deformed", + 3.5 + ] + }, + { + "id": 13, + "type": "SamplerCustomAdvanced", + "pos": { + "0": 1215.767333984375, + "1": 133.8721466064453 + }, + "size": { + "0": 266.6016845703125, + "1": 106 + }, + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "name": "noise", + "type": "NOISE", + "link": 174, + "slot_index": 0, + "label": "noise" + }, + { + "name": "guider", + "type": "GUIDER", + "link": 228, + "slot_index": 1, + "label": "guider" + }, + { + "name": "sampler", + "type": "SAMPLER", + "link": 172, + "slot_index": 2, + "label": "sampler" + }, + { + "name": "sigmas", + "type": "SIGMAS", + "link": 20, + "slot_index": 3, + "label": "sigmas" + }, + { + "name": "latent_image", + "type": "LATENT", + "link": 222, + "slot_index": 4, + "label": "latent_image" + } + ], + "outputs": [ + { + "name": "output", + "type": "LATENT", + "links": [ + 24 + ], + "slot_index": 0, + "shape": 3, + "label": "output" + }, + { + "name": "denoised_output", + "type": "LATENT", + "links": null, + "shape": 3, + "label": "denoised_output" + } + ], + "properties": { + "Node name for S&R": "SamplerCustomAdvanced" + } + }, + { + "id": 87, + "type": "Reroute", + "pos": { + "0": 159.76731872558594, + "1": -170.12783813476562 + }, + "size": [ + 75, + 26 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 238, + "label": "" + } + ], + "outputs": [ + { + "name": "", + "type": "MODEL", + "links": [ + 148, + 227 + ], + "slot_index": 0, + "label": "" + } + ], + "properties": { + "showOutputText": false, + "horizontal": false + } + }, + { + "id": 8, + "type": "VAEDecode", + "pos": { + "0": 1513.767333984375, + "1": 140.87216186523438 + }, + "size": { + "0": 210, + "1": 46 + }, + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 24, + "label": "samples" + }, + { + "name": "vae", + "type": "VAE", + "link": 151, + "label": "vae" + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 127, + 225, + 232 + ], + "slot_index": 0, + "label": "IMAGE" + } + ], + "properties": { + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 134, + "type": "MaskToImage", + "pos": { + "0": 440, + "1": -815 + }, + "size": { + "0": 176.39999389648438, + "1": 29.597196578979492 + }, + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "mask", + "type": "MASK", + "link": 219, + "label": "mask" + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 215 + ], + "slot_index": 0, + "shape": 3, + "label": "IMAGE" + } + ], + "properties": { + "Node name for S&R": "MaskToImage" + } + }, + { + "id": 136, + "type": "PreviewImage", + "pos": { + "0": 668, + "1": -886 + }, + "size": { + "0": 408.4986267089844, + "1": 246 + }, + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 215, + "label": "images" + } + ], + "outputs": [], + "properties": { + "Node name for S&R": "PreviewImage" + } + }, + { + "id": 144, + "type": "ImageCompositeMasked", + "pos": { + "0": 1607, + "1": -460 + }, + "size": { + "0": 315, + "1": 146 + }, + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "name": "destination", + "type": "IMAGE", + "link": 234 + }, + { + "name": "source", + "type": "IMAGE", + "link": 232 + }, + { + "name": "mask", + "type": "MASK", + "link": 236 + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 235 + ], + "slot_index": 0, + "shape": 3 + } + ], + "properties": { + "Node name for S&R": "ImageCompositeMasked" + }, + "widgets_values": [ + 0, + 0, + true + ] + }, + { + "id": 11, + "type": "DualCLIPLoader", + "pos": { + "0": -564.7698974609375, + "1": -22.488271713256836 + }, + "size": { + "0": 315, + "1": 106 + }, + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "CLIP", + "type": "CLIP", + "links": [ + 223 + ], + "slot_index": 0, + "shape": 3, + "label": "CLIP" + } + ], + "properties": { + "Node name for S&R": "DualCLIPLoader" + }, + "widgets_values": [ + "t5xxl_fp16.safetensors", + "clip_l.safetensors", + "flux" + ] + }, + { + "id": 10, + "type": "VAELoader", + "pos": { + "0": -557.7698974609375, + "1": 134.51173400878906 + }, + "size": { + "0": 305.9473876953125, + "1": 68.47245788574219 + }, + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "VAE", + "type": "VAE", + "links": [ + 150 + ], + "slot_index": 0, + "shape": 3, + "label": "VAE" + } + ], + "properties": { + "Node name for S&R": "VAELoader" + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 25, + "type": "RandomNoise", + "pos": { + "0": 825.7671508789062, + "1": 134.8721466064453 + }, + "size": { + "0": 290.9759216308594, + "1": 82 + }, + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "NOISE", + "type": "NOISE", + "links": [ + 174 + ], + "shape": 3, + "label": "NOISE" + } + ], + "properties": { + "Node name for S&R": "RandomNoise" + }, + "widgets_values": [ + 24, + "fixed" + ] + }, + { + "id": 76, + "type": "SaveImage", + "pos": { + "0": 1232, + "1": 312 + }, + "size": { + "0": 367.42144775390625, + "1": 406.4285888671875 + }, + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 127, + "label": "images" + } + ], + "outputs": [], + "title": "Model Output", + "properties": { + "Node name for S&R": "SaveImage" + }, + "widgets_values": [ + "pl" + ] + }, + { + "id": 130, + "type": "LoadImage", + "pos": { + "0": 240, + "1": -611 + }, + "size": { + "0": 417.38385009765625, + "1": 314 + }, + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 205, + 226, + 234 + ], + "slot_index": 0, + "shape": 3, + "label": "IMAGE" + }, + { + "name": "MASK", + "type": "MASK", + "links": [ + 217 + ], + "slot_index": 1, + "shape": 3, + "label": "MASK" + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "clipspace/clipspace-mask-506435.7999997139.png [input]", + "image" + ] + }, + { + "id": 138, + "type": "GrowMaskWithBlur", + "pos": { + "0": 715.314453125, + "1": -571.8499755859375 + }, + "size": { + "0": 315, + "1": 246 + }, + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "mask", + "type": "MASK", + "link": 217, + "label": "mask" + } + ], + "outputs": [ + { + "name": "mask", + "type": "MASK", + "links": [ + 218, + 219, + 236 + ], + "slot_index": 0, + "shape": 3, + "label": "mask" + }, + { + "name": "mask_inverted", + "type": "MASK", + "links": null, + "shape": 3, + "label": "mask_inverted" + } + ], + "properties": { + "Node name for S&R": "GrowMaskWithBlur" + }, + "widgets_values": [ + 0, + 0, + false, + false, + 0, + 1, + 1, + false + ] + }, + { + "id": 16, + "type": "KSamplerSelect", + "pos": { + "0": 823.7671508789062, + "1": 283.8721923828125 + }, + "size": { + "0": 256.2611999511719, + "1": 58 + }, + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 172 + ], + "slot_index": 0, + "shape": 3, + "label": "SAMPLER" + } + ], + "properties": { + "Node name for S&R": "KSamplerSelect" + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 111, + "type": "ShowText|pysssss", + "pos": { + "0": 251, + "1": 518 + }, + "size": { + "0": 407.2326354980469, + "1": 219.7727508544922 + }, + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "name": "text", + "type": "STRING", + "link": 180, + "widget": { + "name": "text" + }, + "label": "text" + } + ], + "outputs": [ + { + "name": "STRING", + "type": "STRING", + "links": [], + "slot_index": 0, + "shape": 6, + "label": "STRING" + } + ], + "properties": { + "Node name for S&R": "ShowText|pysssss" + }, + "widgets_values": [ + "", + "Albert Einstein" + ] + }, + { + "id": 139, + "type": "EmptySD3LatentImage", + "pos": { + "0": 821.7671508789062, + "1": 573.8721313476562 + }, + "size": { + "0": 315, + "1": 106 + }, + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "LATENT", + "type": "LATENT", + "links": [ + 222 + ], + "slot_index": 0, + "shape": 3 + } + ], + "properties": { + "Node name for S&R": "EmptySD3LatentImage" + }, + "widgets_values": [ + 1024, + 1024, + 1 + ] + }, + { + "id": 124, + "type": "Text Concatenate (JPS)", + "pos": { + "0": 312, + "1": -154 + }, + "size": { + "0": 219.5895233154297, + "1": 138 + }, + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "name": "text1", + "type": "STRING", + "link": null, + "widget": { + "name": "text1" + }, + "label": "text1" + }, + { + "name": "text2", + "type": "STRING", + "link": null, + "widget": { + "name": "text2" + }, + "label": "text2" + }, + { + "name": "text3", + "type": "STRING", + "link": null, + "widget": { + "name": "text3" + }, + "label": "text3" + }, + { + "name": "text4", + "type": "STRING", + "link": null, + "widget": { + "name": "text4" + }, + "label": "text4" + }, + { + "name": "text5", + "type": "STRING", + "link": null, + "widget": { + "name": "text5" + }, + "label": "text5" + } + ], + "outputs": [ + { + "name": "text", + "type": "STRING", + "links": [ + 198 + ], + "slot_index": 0, + "shape": 3, + "label": "text" + } + ], + "properties": { + "Node name for S&R": "Text Concatenate (JPS)" + }, + "widgets_values": [ + "comma", + "", + "", + "", + "", + "" + ] + }, + { + "id": 140, + "type": "Image Comparer (rgthree)", + "pos": { + "0": 1613, + "1": 321 + }, + "size": { + "0": 357.58453369140625, + "1": 424.3191223144531 + }, + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "name": "image_a", + "type": "IMAGE", + "link": 225, + "dir": 3 + }, + { + "name": "image_b", + "type": "IMAGE", + "link": 226, + "dir": 3 + } + ], + "outputs": [], + "properties": { + "comparer_mode": "Slide" + }, + "widgets_values": [ + [ + { + "name": "A", + "selected": true, + "url": "/api/view?filename=rgthree.compare._temp_dmora_02633_.png&type=temp&subfolder=&rand=0.39816085595232487" + }, + { + "name": "B", + "selected": true, + "url": "/api/view?filename=rgthree.compare._temp_dmora_02634_.png&type=temp&subfolder=&rand=0.9050946330845266" + } + ] + ] + }, + { + "id": 133, + "type": "ControlNetLoader", + "pos": { + "0": 1109.0059814453125, + "1": -691.749755859375 + }, + "size": { + "0": 435.60980224609375, + "1": 100.55636596679688 + }, + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "CONTROL_NET", + "type": "CONTROL_NET", + "links": [ + 212 + ], + "slot_index": 0, + "shape": 3, + "label": "CONTROL_NET" + } + ], + "properties": { + "Node name for S&R": "ControlNetLoader" + }, + "widgets_values": [ + "0930_inpaint_cn.safetensors" + ] + }, + { + "id": 145, + "type": "PreviewImage", + "pos": { + "0": 2014, + "1": 317 + }, + "size": { + "0": 434.4592590332031, + "1": 423.6662292480469 + }, + "flags": {}, + "order": 28, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 235, + "label": "images" + } + ], + "outputs": [], + "title": "Compose", + "properties": { + "Node name for S&R": "PreviewImage" + } + }, + { + "id": 35, + "type": "StringFunction|pysssss", + "pos": { + "0": 234, + "1": 72 + }, + "size": { + "0": 438.01171875, + "1": 381.4057922363281 + }, + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "text_c", + "type": "STRING", + "link": 198, + "widget": { + "name": "text_c" + }, + "label": "text_c" + } + ], + "outputs": [ + { + "name": "STRING", + "type": "STRING", + "links": [ + 180, + 199, + 200 + ], + "slot_index": 0, + "shape": 3, + "label": "STRING" + } + ], + "properties": { + "Node name for S&R": "StringFunction|pysssss" + }, + "widgets_values": [ + "append", + "no", + "Albert Einstein", + "", + "", + "Albert Einstein" + ] + }, + { + "id": 141, + "type": "CFGGuider", + "pos": { + "0": 1295, + "1": -166 + }, + "size": { + "0": 315, + "1": 98 + }, + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 227 + }, + { + "name": "positive", + "type": "CONDITIONING", + "link": 230 + }, + { + "name": "negative", + "type": "CONDITIONING", + "link": 229 + } + ], + "outputs": [ + { + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 228 + ], + "slot_index": 0, + "shape": 3 + } + ], + "properties": { + "Node name for S&R": "CFGGuider" + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 12, + "type": "UNETLoader", + "pos": { + "0": -558.7698974609375, + "1": -155.48825073242188 + }, + "size": { + "0": 308.9964904785156, + "1": 83.4256591796875 + }, + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 237 + ], + "slot_index": 0, + "shape": 3, + "label": "MODEL" + } + ], + "properties": { + "Node name for S&R": "UNETLoader" + }, + "widgets_values": [ + "flux1-dev-fp8.safetensors", + "fp8_e4m3fn" + ] + }, + { + "id": 17, + "type": "BasicScheduler", + "pos": { + "0": 826, + "1": 410 + }, + "size": { + "0": 315, + "1": 106 + }, + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 148, + "slot_index": 0, + "label": "model" + } + ], + "outputs": [ + { + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 20 + ], + "shape": 3, + "label": "SIGMAS" + } + ], + "properties": { + "Node name for S&R": "BasicScheduler" + }, + "widgets_values": [ + "simple", + 8, + 1 + ] + }, + { + "id": 128, + "type": "ControlNetInpaintingAliMamaApply", + "pos": { + "0": 1080, + "1": -538 + }, + "size": { + "0": 403.1999816894531, + "1": 206 + }, + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "name": "positive", + "type": "CONDITIONING", + "link": 208, + "label": "positive" + }, + { + "name": "negative", + "type": "CONDITIONING", + "link": 209, + "label": "negative" + }, + { + "name": "control_net", + "type": "CONTROL_NET", + "link": 212, + "label": "control_net" + }, + { + "name": "vae", + "type": "VAE", + "link": 207, + "label": "vae" + }, + { + "name": "image", + "type": "IMAGE", + "link": 205, + "label": "image" + }, + { + "name": "mask", + "type": "MASK", + "link": 218, + "label": "mask" + } + ], + "outputs": [ + { + "name": "positive", + "type": "CONDITIONING", + "links": [ + 230 + ], + "slot_index": 0, + "shape": 3, + "label": "positive" + }, + { + "name": "negative", + "type": "CONDITIONING", + "links": [ + 229 + ], + "slot_index": 1, + "shape": 3, + "label": "negative" + } + ], + "properties": { + "Node name for S&R": "ControlNetInpaintingAliMamaApply" + }, + "widgets_values": [ + 1, + 0, + 1 + ] + }, + { + "id": 146, + "type": "LoraLoaderModelOnly", + "pos": { + "0": -196, + "1": -201 + }, + "size": { + "0": 315, + "1": 82 + }, + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 237 + } + ], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 238 + ], + "slot_index": 0, + "shape": 3 + } + ], + "properties": { + "Node name for S&R": "LoraLoaderModelOnly" + }, + "widgets_values": [ + "flux_turbo_v1_1.safetensors", + 1 + ] + } + ], + "links": [ + [ + 20, + 17, + 0, + 13, + 3, + "SIGMAS" + ], + [ + 24, + 13, + 0, + 8, + 0, + "LATENT" + ], + [ + 127, + 8, + 0, + 76, + 0, + "IMAGE" + ], + [ + 147, + 88, + 0, + 72, + 0, + "CLIP" + ], + [ + 148, + 87, + 0, + 17, + 0, + "MODEL" + ], + [ + 150, + 10, + 0, + 89, + 0, + "*" + ], + [ + 151, + 89, + 0, + 8, + 1, + "VAE" + ], + [ + 172, + 16, + 0, + 13, + 2, + "SAMPLER" + ], + [ + 174, + 25, + 0, + 13, + 0, + "NOISE" + ], + [ + 180, + 35, + 0, + 111, + 0, + "STRING" + ], + [ + 198, + 124, + 0, + 35, + 0, + "STRING" + ], + [ + 199, + 35, + 0, + 72, + 1, + "STRING" + ], + [ + 200, + 35, + 0, + 72, + 2, + "STRING" + ], + [ + 205, + 130, + 0, + 128, + 4, + "IMAGE" + ], + [ + 207, + 89, + 0, + 128, + 3, + "VAE" + ], + [ + 208, + 72, + 0, + 128, + 0, + "CONDITIONING" + ], + [ + 209, + 131, + 0, + 128, + 1, + "CONDITIONING" + ], + [ + 210, + 88, + 0, + 131, + 0, + "CLIP" + ], + [ + 212, + 133, + 0, + 128, + 2, + "CONTROL_NET" + ], + [ + 215, + 134, + 0, + 136, + 0, + "IMAGE" + ], + [ + 217, + 130, + 1, + 138, + 0, + "MASK" + ], + [ + 218, + 138, + 0, + 128, + 5, + "MASK" + ], + [ + 219, + 138, + 0, + 134, + 0, + "MASK" + ], + [ + 222, + 139, + 0, + 13, + 4, + "LATENT" + ], + [ + 223, + 11, + 0, + 88, + 0, + "*" + ], + [ + 225, + 8, + 0, + 140, + 0, + "IMAGE" + ], + [ + 226, + 130, + 0, + 140, + 1, + "IMAGE" + ], + [ + 227, + 87, + 0, + 141, + 0, + "MODEL" + ], + [ + 228, + 141, + 0, + 13, + 1, + "GUIDER" + ], + [ + 229, + 128, + 1, + 141, + 2, + "CONDITIONING" + ], + [ + 230, + 128, + 0, + 141, + 1, + "CONDITIONING" + ], + [ + 232, + 8, + 0, + 144, + 1, + "IMAGE" + ], + [ + 234, + 130, + 0, + 144, + 0, + "IMAGE" + ], + [ + 235, + 144, + 0, + 145, + 0, + "IMAGE" + ], + [ + 236, + 138, + 0, + 144, + 2, + "MASK" + ], + [ + 237, + 12, + 0, + 146, + 0, + "MODEL" + ], + [ + 238, + 146, + 0, + 87, + 0, + "*" + ] + ], + "groups": [ + { + "title": "AliMama Inpainting", + "bounding": [ + 214, + -963, + 1341, + 687 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "title": "FLUX-Text2Image", + "bounding": [ + 146, + -241, + 1747, + 989 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "title": "Load Model", + "bounding": [ + -585, + -250, + 365, + 491 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "config": {}, + "extra": { + "ds": { + "scale": 0.6115909044841532, + "offset": [ + 876.5983955698489, + 1007.0029507778453 + ] + }, + "workspace_info": { + "id": "sSr80zkRsolLQHBh3oFSe", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + }, + "0246.VERSION": [ + 0, + 0, + 4 + ] + }, + "version": 0.4 +} \ No newline at end of file diff --git a/workflows/t2I_flux_turbo.json b/workflows/t2I_flux_turbo.json new file mode 100644 index 0000000..47983a4 --- /dev/null +++ b/workflows/t2I_flux_turbo.json @@ -0,0 +1,528 @@ +{ + "last_node_id": 106, + "last_link_id": 196, + "nodes": [ + { + "id": 4, + "type": "DualCLIPLoader", + "pos": { + "0": -182.46112060546875, + "1": 35.274688720703125 + }, + "size": { + "0": 315, + "1": 106 + }, + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "CLIP", + "type": "CLIP", + "links": [ + 2, + 27 + ], + "slot_index": 0, + "shape": 3, + "label": "CLIP" + } + ], + "properties": { + "Node name for S&R": "DualCLIPLoader" + }, + "widgets_values": [ + "clip_l.safetensors", + "t5xxl_fp16.safetensors", + "flux" + ] + }, + { + "id": 7, + "type": "VAEDecode", + "pos": { + "0": 1028, + "1": -107 + }, + "size": { + "0": 210, + "1": 46 + }, + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 6, + "slot_index": 0, + "label": "samples" + }, + { + "name": "vae", + "type": "VAE", + "link": 7, + "label": "vae" + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 79 + ], + "slot_index": 0, + "shape": 3, + "label": "IMAGE" + } + ], + "properties": { + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 6, + "type": "EmptyLatentImage", + "pos": { + "0": 665, + "1": -145 + }, + "size": { + "0": 315, + "1": 106 + }, + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "LATENT", + "type": "LATENT", + "links": [ + 177 + ], + "slot_index": 0, + "shape": 3, + "label": "LATENT" + } + ], + "properties": { + "Node name for S&R": "EmptyLatentImage" + }, + "widgets_values": [ + 832, + 1248, + 1 + ] + }, + { + "id": 19, + "type": "CLIPTextEncodeFlux", + "pos": { + "0": 206, + "1": 116 + }, + "size": { + "0": 400, + "1": 200 + }, + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 27, + "slot_index": 0, + "label": "clip" + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 26 + ], + "slot_index": 0, + "shape": 3, + "label": "CONDITIONING" + } + ], + "properties": { + "Node name for S&R": "CLIPTextEncodeFlux" + }, + "widgets_values": [ + "", + "(bad hand,bad finger),logo,Backlight,nsfw,(worst quality,low resolution,bad hands),distorted,twisted,watermark,", + 3.5 + ] + }, + { + "id": 5, + "type": "CLIPTextEncodeFlux", + "pos": { + "0": 202, + "1": -146 + }, + "size": { + "0": 400, + "1": 200 + }, + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 2, + "slot_index": 0, + "label": "clip" + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 18 + ], + "slot_index": 0, + "shape": 3, + "label": "CONDITIONING" + } + ], + "properties": { + "Node name for S&R": "CLIPTextEncodeFlux" + }, + "widgets_values": [ + "((Asian Face)), baby girl, age 2, , , , , , , , , , (falling white curtain as background, minimalist, white tone, very soft, bright), photography, masterpiece, best quality, 8K, HDR, highres, front to camera", + "((Asian Face)), baby girl, age 2, , , , , , , , , , (falling white curtain as background, minimalist, white tone, very soft, bright), photography, masterpiece, best quality, 8K, HDR, highres, front to camera", + 3.5 + ] + }, + { + "id": 55, + "type": "UNETLoader", + "pos": { + "0": -177, + "1": 204 + }, + "size": { + "0": 308.9964904785156, + "1": 83.4256591796875 + }, + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 195 + ], + "slot_index": 0, + "shape": 3, + "label": "MODEL" + } + ], + "properties": { + "Node name for S&R": "UNETLoader" + }, + "widgets_values": [ + "flux1-dev-fp8.safetensors", + "fp8_e4m3fn" + ] + }, + { + "id": 106, + "type": "LoraLoaderModelOnly", + "pos": { + "0": -184, + "1": 375 + }, + "size": { + "0": 315, + "1": 82 + }, + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 195 + } + ], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 196 + ], + "shape": 3, + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoraLoaderModelOnly" + }, + "widgets_values": [ + "flux_turbo_v1_1.safetensors", + 1 + ] + }, + { + "id": 8, + "type": "VAELoader", + "pos": { + "0": -179.46112060546875, + "1": -70.72531127929688 + }, + "size": { + "0": 315, + "1": 58 + }, + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "VAE", + "type": "VAE", + "links": [ + 7 + ], + "slot_index": 0, + "shape": 3, + "label": "VAE" + } + ], + "properties": { + "Node name for S&R": "VAELoader" + }, + "widgets_values": [ + "ae.safetensors" + ] + }, + { + "id": 3, + "type": "XlabsSampler", + "pos": { + "0": 654, + "1": 12 + }, + "size": { + "0": 342.5999755859375, + "1": 282 + }, + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 196, + "slot_index": 0, + "label": "model" + }, + { + "name": "conditioning", + "type": "CONDITIONING", + "link": 18, + "label": "conditioning" + }, + { + "name": "neg_conditioning", + "type": "CONDITIONING", + "link": 26, + "label": "neg_conditioning" + }, + { + "name": "latent_image", + "type": "LATENT", + "link": 177, + "label": "latent_image" + }, + { + "name": "controlnet_condition", + "type": "ControlNetCondition", + "link": null, + "label": "controlnet_condition" + } + ], + "outputs": [ + { + "name": "latent", + "type": "LATENT", + "links": [ + 6 + ], + "shape": 3, + "label": "latent" + } + ], + "properties": { + "Node name for S&R": "XlabsSampler" + }, + "widgets_values": [ + 24, + "fixed", + 8, + 1, + 2, + 0, + 1 + ] + }, + { + "id": 21, + "type": "PreviewImage", + "pos": { + "0": 1026, + "1": 19 + }, + "size": { + "0": 210, + "1": 318 + }, + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 79, + "slot_index": 0, + "label": "images" + } + ], + "outputs": [], + "title": "t2i output", + "properties": { + "Node name for S&R": "PreviewImage" + } + } + ], + "links": [ + [ + 2, + 4, + 0, + 5, + 0, + "CLIP" + ], + [ + 6, + 3, + 0, + 7, + 0, + "LATENT" + ], + [ + 7, + 8, + 0, + 7, + 1, + "VAE" + ], + [ + 18, + 5, + 0, + 3, + 1, + "CONDITIONING" + ], + [ + 26, + 19, + 0, + 3, + 2, + "CONDITIONING" + ], + [ + 27, + 4, + 0, + 19, + 0, + "CLIP" + ], + [ + 79, + 7, + 0, + 21, + 0, + "IMAGE" + ], + [ + 177, + 6, + 0, + 3, + 3, + "LATENT" + ], + [ + 195, + 55, + 0, + 106, + 0, + "MODEL" + ], + [ + 196, + 106, + 0, + 3, + 0, + "MODEL" + ] + ], + "groups": [ + { + "title": "Load Model", + "bounding": [ + -210, + -187, + 371, + 700 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "config": {}, + "extra": { + "ds": { + "scale": 1.1918176537727374, + "offset": [ + 438.12831553640723, + 376.2590792694179 + ] + } + }, + "version": 0.4 +} \ No newline at end of file