Txt&Pix2Pix Combo
created 9 months ago
character
img2img
lora
31 nodes

3.0k

511

Outputs
example image output 0 for workflow.
example image output 1 for workflow.
example image output 2 for workflow.
example image output 3 for workflow.
example image output 4 for workflow.
example image output 5 for workflow.
example image output 6 for workflow.
example image output 7 for workflow.
example image output 8 for workflow.
example image output 9 for workflow.
example image output 10 for workflow.
example image output 11 for workflow.
example image output optimized_comfy_workflows_user_uploads/8fe878d1-2ff9-410e-b2cb-cd1a6ea52126/assets/Di (1).webp for workflow.
Description

Diffusionaiart.com Fine-Tuned Workflows | GENERATE & EDIT SIMPLY BY PROMPTING | FOR CHANGING STYLE, COLOR, ELEMENTS, AND CHARACTERS

Pix2Pix Text to Image, Image to Image Combo v1 (❁´◡`❁)

We're excited to release our advanced diffusion workflows—completely free for the community, with more on the way.

Features:

  • Text and Image to Image Style Transfer in a single workflow; simply toggle switches. (✿´‿`)

  • Photo Editing

  • Fast and Optimized

  • Detailed Generations and Transfers

  • Nvidia Align Your Steps & AutoCFG

  • Perfectly Sharp Images

  • Over 400 Styles

  • You can add your tags and triggers.

  • Ready for live deployment.

To use ChatGPT3.5 LLM you need to add environment variable for OPENAI_API_KEY, simply search for "Edit the System Environment Variables..." on Windows, click on the Environment Variables and from there click on "New" under user variables, and add your open ai key like this: OPENAI_API_KEY as variable name and key as variable value.

Usage:

  1. Toggle switches to 1 or 2 to enable IMG2IMG or LLM Enhance (ChatGPT 3.5 Turbo). (❁´◡`❁)

  2. Upload your photo or add your positive prompt depending on the mode you're using (Text2Image, Image2Image). (˶◕‿◕˶✿)

  3. Add styles by typing <1>, <311>, etc., in the prompt area. The styles list extends up to the 400s.

  4. While these are my creations, this specific workflow performs best with user-written prompts.

You can also check out https://www.diffusionaiart.com and we have an awesome Pix2Pix generator over there that is completely free to use as well as other diffusion techniques like Layer Diffusion, upscaling, loras and different models.

Simplified version without ChatGPT (NegiTools) is also added.

Comfyui Commit Version: 7990ae18c1df1dc18b0f1197c9e09551c202c829

Nodes Used:

  • Automatic CFG (01bf4faaf1b10026cb87fd0e9fe15f5acbe5d780),

  • ComfyRoll Studio (d78b780ae43fcf8c6b7c6505e6ffb4584281ceca),

  • Extended Save Image (588fa79aec290b78ce419b23756ed9e1ccff46fb),

  • Hakkun-ComfyUI-nodes (dd951bb32210a23dd75510e79ce3440ea33125f5),

  • Was Node Suite (6c3fed70655b737dc9b59da1cadb3c373c08d8ed),

  • ComfyUI-NegiTools (f82c13aa1de85203f51847084e94963d0d6bb214),

  • pythongosssss/ComfyUI-Custom-Scripts (3f2c021e50be2fed3c9d1552ee8dcaae06ad1fe5),

  • ComfyUI Deploy (b0b1d64b6b5cb0a4f6d4a9a87416da7421015ea5)

Thanks to StabilityAI for their fantastic models and custom model trainer. https://civitai.com/user/Ciro_Negrogni

THIS MODEL and WORKFLOW CANNOT BE COMMERCIALIZED DUE TO STABILITY AI LICENSING. BEWARE. (✿◠‿◠)

Built-in nodes
InstructPixToPixConditioning
Custom nodes
LoraLoader
Automatic CFG
Prompt Parser
Text Multiline
CLIPTextEncodeSDXL
VAEDecode
EmptyLatentImage
ImageSharpen
ComfyUIDeployExternalNumberInt
NegiTools_OpenAiGpt
CR Combine Prompt
CR Conditioning Input Switch
CR Text Input Switch
LoadImage
CR Latent Batch Size
CR Latent Input Switch
ComfyUIDeployExternalImage
ComfyUIDeployExternalText
ConstrainImage|pysssss
CheckpointLoaderSimple
SaveImageExtended
AlignYourStepsScheduler
KSamplerSelect
SamplerCustom
Custom files
new

These are separate files that the creator has uploaded for this workflow.

TxtPix2PixSimplified.json

Models
0
0
0
0